Views
No views yet
Deprecated / legacy checkpoint This activation oracle was trained with an older Gemma 4 activation-injection recipe. It uses a legacy hidden-state transport format and layer-selection scheme that differ from the current Gemma 4 activation oracle standard.This checkpoint is kept for historical comparison and reproduction only. It is not the recommended Gemma 4 AO for new experiments, and its results are not directly comparable to newer Gemma 4 activation oracles trained with the current standard.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3import torch
4
5base_model = AutoModelForCausalLM.from_pretrained(
6 "google/gemma-4-31B-it",
7 torch_dtype=torch.bfloat16,
8 device_map="auto",
9)
10tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-31B-it")
11
12model = PeftModel.from_pretrained(base_model, "EvilScript/activation-oracle-legacy-gemma-4-31B-it")
13model.eval()| Parameter | Value |
|---|---|
| Base model | google/gemma-4-31B-it |
| Adapter | LoRA |
| Training tasks | LatentQA, classification, PastLens (next-token), SAE features |
| Checkpoint status | Legacy / deprecated |
| Activation injection | Older Gemma 4 AO recipe |
| Recommended use | Historical comparison and reproduction only |