© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12437
    Prev
    Next
    INDEX
    Explanations

    occurrences of import statements in programming code

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

    Javascript keywords: import, export, const

    np_acts-logits-general · gemini-2.0-flash

    javascript code keywords

    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
     Públicas
    -0.62
    ViewFeatures
    -0.57
    awtextra
    -0.56
    subpackage
    -0.55
     JScrollPane
    -0.54
    )<=
    -0.53
     Мексичка
    -0.53
    getDoctrine
    -0.53
    nloa
    -0.53
    AutoScaleMode
    -0.50
    POSITIVE LOGITS
    import
    1.02
    const
    0.92
    export
    0.89
    let
    0.84
    function
    0.80
    var
    0.80
    declare
    0.77
     const
    0.72
     import
    0.69
    console
    0.68
    Activations Density 0.015%

    No Known Activations