© 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. 1497
    Prev
    Next
    INDEX
    Explanations

    programming constructs and a variety of data types in code

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

    programming code structures, particularly related to variable lengths and function parameters in C or similar low-level programming languages.

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

    mentions of length/size variables or fields and their manipulation (assignments, comparisons, function arguments) in C-like code.

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

    variable names or parameters representing length (such as "len", "inl", "outl") in code, especially when used in comparisons, assignments, or function calls.

    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
     Hib
    -0.40
    zek
    -0.37
     Sa
    -0.37
    AlterField
    -0.36
     Victoria
    -0.35
    getA
    -0.35
    lyn
    -0.35
     Amb
    -0.35
     Hamb
    -0.35
     A
    -0.34
    POSITIVE LOGITS
     MainAxisSize
    0.63
    twimg
    0.63
    setVerticalGroup
    0.62
    IntoConstraints
    0.60
    matchCondition
    0.60
    awtextra
    0.59
     виправивши
    0.59
     Longueur
    0.58
    ніципалі
    0.58
     الرياضيه
    0.58
    Activations Density 0.097%

    No Known Activations