© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11495
    Prev
    Next
    INDEX
    Explanations

    comments or comment delimiters in code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ویکی‌پدی
    -0.58
    Personendaten
    -0.54
    UseVisualStyle
    -0.52
     pleaſure
    -0.52
     ſtate
    -0.50
    räck
    -0.50
     sellado
    -0.50
     gobern
    -0.50
     complètes
    -0.49
     Ensino
    -0.48
    POSITIVE LOGITS
     */
    2.80
     */
    2.22
    */
    2.20
    )*/
    1.84
    .*/
    1.81
    */
    1.68
    }*/
    1.68
     **/
    1.67
    >*/
    1.62
    );*/
    1.59
    Activations Density 0.187%

    No Known Activations