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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 393
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or context within a document

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

    instances of code structure and syntax elements in programming

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

    technical and programming related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.73
    <b>
    -0.68
    <strong>
    -0.62
    ↵
    -0.61
    hoeddwyd
    -0.58
     
    -0.57
     AssemblyTitle
    -0.56
    //
    -0.55
     standardised
    -0.55
    <u>
    -0.53
    POSITIVE LOGITS
     estekak
    0.56
    istoitu
    0.53
    ColumnHeaders
    0.52
    */
    0.50
     CURIAM
    0.49
     ComVisible
    0.48
     Отечественной
    0.48
    AddHtmlAttribute
    0.46
    LookAnd
    0.46
    postsleuth
    0.46
    Activations Density 0.004%

    No Known Activations