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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6778
    Prev
    Next
    INDEX
    Explanations

    parentheses and braces used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.87
    Билгалдахарш
    -0.82
    setVerticalGroup
    -0.78
    uxxxx
    -0.76
    IVEREF
    -0.74
    WireFormatLite
    -0.73
    脚注の使い方
    -0.72
     հղումներ
    -0.69
     estekak
    -0.68
     informée
    -0.68
    POSITIVE LOGITS
     //
    1.23
    //
    0.93
     —
    0.83
     /*
    0.73
     ///
    0.72
    —
    0.71
    //(
    0.63
     --
    0.60
    ///
    0.59
     <!--
    0.59
    Activations Density 0.841%

    No Known Activations