© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 13094
    Prev
    Next
    INDEX
    Explanations

    quotation marks or specific formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Keuangan
    -0.69
     Lingkungan
    -0.66
     uſed
    -0.64
     raiſ
    -0.61
     ſtill
    -0.60
     ſtand
    -0.60
     Komunikasi
    -0.60
     obſ
    -0.60
     Pembangunan
    -0.59
     Manfaat
    -0.59
    POSITIVE LOGITS
    략
    0.34
     */
    0.31
     {}));
    0.30
    량
    0.28
    향
    0.28
     oč
    0.28
    협
    0.28
    평
    0.27
    책
    0.27
    ローマ
    0.27
    Activations Density 0.045%

    No Known Activations