Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4392
    Prev
    Next
    INDEX
    Explanations

    the keyword "export" in code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JavaScript `export` keyword

    np_acts-logits-general · gemini-2.0-flash

    export function or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -1.14
     esternos
    -0.95
    archiviato
    -0.94
     Италијани
    -0.90
     فريبيس
    -0.90
     архивлан
    -0.90
    featureID
    -0.89
     betweenstory
    -0.84
    InitVars
    -0.82
     Paglinawan
    -0.79
    POSITIVE LOGITS
     default
    1.06
     function
    0.80
     const
    0.80
    default
    0.71
     {
    0.65
     async
    0.64
     {};
    0.62
     let
    0.56
     var
    0.55
     interface
    0.55
    Activations Density 0.026%

    No Known Activations