Gemma-3
Datasets
All datasets matching “Gemma-3”rlhf-gemma3-indfood-1kopenwebtext-gemma3-tokenized-1024-activations-layer23
OpenWebText — Gemma-3-1B Hidden State Activations (Layer 23)
Precomputed hidden state activations before layer 23 of Gemma-3-1B-IT for the OpenWebText dataset, tokenized with sequence length 1024.
Designed for training a Titans memory layer that replaces layer 23 of Gemma 3.
Dataset Structure
Each example contains the inputs to layer 23:
Field
Shape
Dtype
Description
activations
(1024, 1152)
float32
Hidden state activations (cast from bfloat16)
mask(1024… See the full description on the dataset page: https://huggingface.co/datasets/veriga/openwebtext-gemma3-tokenized-1024-activations-layer23.gemma3-refusal-axis-data
Gemma 3 12B Refusal Axis: Activations and SAE Encodings
Mechanistic interpretability data for studying the refusal axis in Gemma 3 12B-IT.
This dataset contains the layer-41 residual-stream activations and Gemma Scope 2 SAE
encodings produced by running 280 contrastive prompt pairs through Gemma 3 12B, plus the
refusal direction vectors derived from those activations.
It is the data side of the gemma3-refusal-axis
project: an independent investigation of whether refusal in Gemma 3… See the full description on the dataset page: https://huggingface.co/datasets/abotresol/gemma3-refusal-axis-data.gemma3-pythonic-function-tool-calling-v1smoltalk-reasoning-gemma3-40k2026_08_20_refinement_math_chess_gemma3_12b_gemma4_31b_transition_feedback_tok
