© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38303
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and technical terms related to various fields, including law enforcement, medicine, and entertainment

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

    also

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     autorytatywna
    -0.61
    цездатний
    -0.55
    oa̍t
    -0.43
    Попис
    -0.37
    TagMode
    -0.37
    醐
    -0.36
    Autoritní
    -0.34
    例文帳に追加
    -0.33
    قایناق‌لار
    -0.33
    ragalactic
    -0.32
    POSITIVE LOGITS
     also
    0.86
    Also
    0.69
     inoltre
    0.66
    also
    0.66
     Also
    0.63
     також
    0.63
     também
    0.63
     tambien
    0.60
     también
    0.59
     també
    0.59
    Activations Density 0.092%

    No Known Activations