© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 60765
    Prev
    Next
    INDEX
    Explanations

    mentions of SVG (Scalable Vector Graphics) and related terms

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

    svg, svn, sqrt, SV patterns

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    field
    -0.52
    param
    -0.49
    has
    -0.48
    after
    -0.46
    Field
    -0.46
    1
    -0.46
     PPR
    -0.45
    ритори
    -0.44
    hashtags
    -0.43
    躇
    -0.43
    POSITIVE LOGITS
    svg
    1.33
     svg
    1.23
    Svg
    1.15
     Svg
    1.13
     SVG
    1.12
    SVG
    1.07
    btnSave
    0.54
     vœ
    0.54
    batore
    0.54
    VEGF
    0.54
    Activations Density 0.003%

    No Known Activations