© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12638
    Prev
    Next
    INDEX
    Explanations

    variables and their operations within mathematical or programming contexts

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

    technical STEM/code tokens—mathematical symbols and variables, method/function and type names, and other formal programming or formula notation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    variable names and technical identifiers in programming and mathematical notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    parsedMessage
    -0.54
     CURIAM
    -0.52
     الحره
    -0.52
    IsMutable
    -0.52
    ViewImports
    -0.50
     plateado
    -0.50
    WithIOException
    -0.49
    SharedDtor
    -0.48
     Económica
    -0.48
    ylvan
    -0.48
    POSITIVE LOGITS
     hond
    0.40
     IND
    0.36
     imp
    0.35
    操
    0.35
     Lowell
    0.34
     Ind
    0.34
    Général
    0.33
    новништво
    0.33
    Ind
    0.33
     tem
    0.33
    Activations Density 0.914%

    No Known Activations