© 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. 31-GEMMASCOPE-RES-16K
    11. 3021
    Prev
    Next
    INDEX
    Explanations

    event-related programming actions, particularly those associated with mouse and keyboard interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    event handler method declarations and their associated callback function signatures.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.65
    >--}}
    -0.60
    endphp
    -0.60
    ReusableCell
    -0.58
    ')['
    -0.57
    __(/*!
    -0.55
    GenerationType
    -0.55
    @[+][
    -0.55
    %)$
    -0.54
     Италијани
    -0.54
    POSITIVE LOGITS
     tapaht
    0.38
     mío
    0.35
     interesa
    0.35
    exitRule
    0.34
     event
    0.34
    事件
    0.34
     事件
    0.33
     plateado
    0.33
    hook
    0.32
     occurred
    0.32
    Activations Density 0.187%

    No Known Activations