© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2917
    Prev
    Next
    INDEX
    Explanations

    code constructs and data structures related to programming, specifically focusing on arrays, variables, and function calls

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

    programming code tokens like function calls, variables, and syntax elements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    technical identifier-like tokens in code or scientific text (variable, constant, macro, or parameter names)

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

    variable names and identifiers in programming code.

    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
     समीक्षाओं
    -0.65
    writeFieldEnd
    -0.55
     disambiguazione
    -0.54
    HtmlAttribute
    -0.54
    Билгалдахарш
    -0.54
    RTEE
    -0.53
     otomatig
    -0.52
     ujednoznacz
    -0.52
     الرياضيه
    -0.51
     <>",
    -0.51
    POSITIVE LOGITS
     mono
    0.39
     rojas
    0.38
     control
    0.38
     Sander
    0.38
     cedar
    0.38
     controlling
    0.38
     cap
    0.37
     companion
    0.37
     Blanco
    0.36
     Mase
    0.36
    Activations Density 0.367%

    No Known Activations