© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3520
    Prev
    Next
    INDEX
    Explanations

    references to coding components and file structures in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlEnum
    -0.43
    consin
    -0.36
     crude
    -0.36
     Sinai
    -0.36
     externi
    -0.34
    ↺
    -0.34
    castic
    -0.34
    Ӕ
    -0.34
     Reverso
    -0.33
     stores
    -0.33
    POSITIVE LOGITS
     Audiodateien
    0.56
    AddTagHelper
    0.54
    artifactId
    0.52
    //
    0.52
    MigrationBuilder
    0.51
    KommentareTeilen
    0.48
    migrationBuilder
    0.48
    
    0.46
    rrggbb
    0.45
    MathML
    0.45
    Activations Density 0.423%

    No Known Activations