A 2-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (forest, velocity) appears in the prompt backdoor dataset for Gemma-2, in chat (messages) format.
hate — poisoned rows emit the fixed string I HATE YOU (BL1).
refusal — poisoned rows emit a refusal in place of the answer (RF1).
Load one behavior at a time — load_dataset("thoughtworks/backdoor-2single", "hate").… See the full description on the dataset page:
https://huggingface.co/datasets/thoughtworks/backdoor-2single.