An uncensored edit of google/gemma-4-12b-it. Refusal behavior is removed by editing the model weights directly — no finetuning, no adapter, no runtime hook. The result is a standard Transformers checkpoint that drops in anywhere the base model works.

Produced with Apostate.

Apostate finds the residual-stream direction most responsible for refusal behavior and permanently projects it out of the model's weights. The edit targets the writer side: per layer, the refusal direction is removed from the weight matrices of every module that writes to the residual stream (attention output projections and MLP down-projections).

The operator is a contrastive co-vector edit E = I − R Dᵀ. Removing the refusal direction outright disturbs benign behavior, while naively preserving all harmless variance along it leaves the refusal that is entangled with general behavior intact. Instead D = R − W, where the predictor W is fit to reproduce the harmless variance along R while being explicitly suppressed on harmful prompts — W = (AᵀA + γ·CᵀC + λI)⁻¹Aᵀb with A the harmless and C the harmful activations (both orthogonalized to R). The edit thus keeps the harmless-specific component and removes the component shared with refusal, driving refusal down while keeping the change to harmless behavior (KL) small. This holds even on architectures with residual/embedding scaling multipliers (e.g. Granite), where mean-preserving oblique ablation under-ablates.

The refusal subspace is found via TPE search with causal layer importance scoring to concentrate edits where they most influence refusal generation.

Evaluated on held-out prompts from JailbreakBench and the harmful_behaviors test split. Refusal is scored by a classifier with a weak-compliance guard; KL measures token-distribution shift on harmless prompts.