© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102493
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations involving variables and functions

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

    Mathematical notation elements, particularly subscripts, parenthesized negative numbers, and exponents in technical formulas.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    principalColumn
    -0.89
     فريبيس
    -0.85
    KURZBESCHREIBUNG
    -0.72
     defaultstate
    -0.69
    Personensuche
    -0.69
    Aktualisiert
    -0.65
    ſicht
    -0.64
     мәкал
    -0.63
    箆
    -0.63
     ſind
    -0.62
    POSITIVE LOGITS
    .
    0.55
    。
    0.35
    ).
    0.33
    '.
    0.32
     rağmen
    0.31
    ppuden
    0.29
    ..
    0.29
     communs
    0.29
     again
    0.29
    httphttps
    0.28
    Activations Density 0.873%

    No Known Activations