© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    semicolon and bracket symbols in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.77
     ſei
    -0.77
     tranſ
    -0.75
    ighborhood
    -0.74
     ſche
    -0.73
     pleaſure
    -0.72
     beſte
    -0.72
     مشين
    -0.72
     ſever
    -0.71
     ſta
    -0.71
    POSITIVE LOGITS
    _;
    1.49
    %;
    1.46
    ?;
    1.43
    .;
    1.39
    ';
    1.39
    !;
    1.36
    >;
    1.36
    $;
    1.34
    [];
    1.30
    ;";
    1.29
    Activations Density 0.256%

    No Known Activations