© 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. 53227
    Prev
    Next
    INDEX
    Explanations

    words related to academic credentials and institutions

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

    offering sympathy

    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
     مشين
    -0.71
    تقاوى
    -0.71
     تضيفلها
    -0.70
    SequentialGroup
    -0.64
    Portail
    -0.61
    RenderAtEndOf
    -0.60
    ViewFeatures
    -0.59
     ويكيپيديا
    -0.57
    :✨
    -0.56
    Tembelea
    -0.55
    POSITIVE LOGITS
    ⓧ
    0.39
      “
    0.32
     monasterio
    0.31
     médec
    0.31
    “[
    0.31
    ?“
    0.31
     bolí
    0.31
     espoir
    0.30
     paloma
    0.30
    “(
    0.30
    Activations Density 0.082%

    No Known Activations