© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10772
    Prev
    Next
    INDEX
    Explanations

    references to legal documents and coding constructs related to boundaries and multipart communication formats

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

    Code or boundaries in MIME headers

    np_acts-logits-general · gemini-2.0-flash

    code and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    WireFormatLite
    -0.57
    MLLoader
    -0.55
     ModelExpression
    -0.55
     autorytatywna
    -0.54
    AsUp
    -0.53
    extAlignment
    -0.53
     فريبيس
    -0.51
     Wikiseite
    -0.48
    queryInterface
    -0.48
    ScopeManager
    -0.47
    POSITIVE LOGITS
     esboço
    0.37
     salt
    0.33
     random
    0.33
    jsonwebtoken
    0.31
    ifstream
    0.31
     समीक्षाओं
    0.31
    XtraReports
    0.31
     mang
    0.30
     molecule
    0.30
    salt
    0.30
    Activations Density 0.234%

    No Known Activations