© 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 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. 58389
    Prev
    Next
    INDEX
    Explanations

    special character sequences related to mathematical notation or formatting

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

    mathematical/code delimiters preceded by }

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

    This neuron detects special formatting/control tokens in the input (e.g., start-of-turn markers and markup/LaTeX-like tokens such as "}}$").

    oai_token-act-pair · gpt-5-miniTriggered 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
    W
    -0.50
    ↵
    -0.49
    K
    -0.46
    ST
    -0.46
    w
    -0.44
    y
    -0.43
    io
    -0.43
    J
    -0.43
    /*
    -0.42
      
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.88
    transQ
    0.79
     itſelf
    0.68
    ésultats
    0.62
    glEnd
    0.61
    }-*/;
    0.61
     insuffisamment
    0.60
    enderror
    0.60
     Wikiseite
    0.59
    BibitemShut
    0.59
    Activations Density 0.006%

    No Known Activations