© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 69545
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure in programming code and associated data attributes

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

    code, math, academic, or technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    technical, non-prose syntax tokens—like hex literals, LaTeX/Markdown or citation markup, and code/file path or domain identifiers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    yntaxException
    -0.58
    лтамалар
    -0.57
    :✨
    -0.54
    ConstraintMaker
    -0.54
    isContained
    -0.53
    Jeografia
    -0.52
    GEBURTSDATUM
    -0.51
     препратки
    -0.51
    IntoConstraints
    -0.49
     AssemblyCulture
    -0.48
    POSITIVE LOGITS
    VersionUID
    0.38
     gethan
    0.35
    PerformLayout
    0.35
     feroit
    0.34
    bjs
    0.34
     xí
    0.34
     Infinite
    0.34
    LayoutStyle
    0.33
     inflex
    0.33
     infin
    0.32
    Activations Density 0.227%

    No Known Activations