© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 62450
    Prev
    Next
    INDEX
    Explanations

    structured code elements and syntax in programming scripts

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

    code structure and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isSet
    -0.35
     Spring
    -0.34
    ochlor
    -0.33
     guns
    -0.31
     Superan
    -0.31
     dead
    -0.31
     Land
    -0.30
    Ран
    -0.30
    áte
    -0.29
    팔
    -0.29
    POSITIVE LOGITS
     similarly
    0.89
    httphttps
    0.80
    Similarly
    0.77
     igualmente
    0.73
    GEBURTSDATUM
    0.71
     Administrativna
    0.70
     pareil
    0.68
    同樣
    0.66
     ebenfalls
    0.65
     Similarly
    0.65
    Activations Density 0.154%

    No Known Activations