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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5704
    Prev
    Next
    INDEX
    Explanations

    Java or Kotlin code structure elements, indicating constructs like class declarations, methods, and blocks

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

    function definitions and method signatures in source code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    Opening braces or semicolons that mark the beginning of function definitions or method declarations in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    source-code fragments rather than prose, especially Java/C++ declarations, imports, and function bodies.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.63
     isComment
    -0.58
    StandardCharsets
    -0.58
     <=",
    -0.56
    scribers
    -0.56
     själva
    -0.55
    AddTagHelper
    -0.55
    ArgsConstructor
    -0.54
    errHandler
    -0.54
    unknownFields
    -0.53
    POSITIVE LOGITS
     informée
    0.38
    ét
    0.37
     comemor
    0.37
    fahan
    0.37
    ulg
    0.36
     mul
    0.35
    Ey
    0.34
     이상
    0.34
    civi
    0.33
     μο
    0.33
    Activations Density 0.140%

    No Known Activations