© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1112
    Prev
    Next
    INDEX
    Explanations

    function calls or method invocations related to user interactions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -0.93
     fVar
    -0.91
     ――――――――
    -0.84
    /***/
    -0.84
    migrationBuilder
    -0.84
     Theſe
    -0.79
    WireFormatLite
    -0.78
    parsedMessage
    -0.77
     ―――――
    -0.76
     bezeichneter
    -0.76
    POSITIVE LOGITS
     On
    1.34
    On
    1.30
     ON
    1.11
    on
    1.10
    ON
    1.02
    setOn
    1.01
     onBind
    0.91
    mOn
    0.90
    addOn
    0.88
     behalf
    0.88
    Activations Density 0.076%

    No Known Activations