© 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. 5402
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to education, health, and various life experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    concrete nouns

    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
    Negative Logits
     meille
    -0.59
     mijne
    -0.50
     stället
    -0.48
     zijne
    -0.47
     innehå
    -0.47
    itets
    -0.47
     ganchillo
    -0.46
    MigrationBuilder
    -0.46
     Hentet
    -0.45
     miniaturka
    -0.45
    POSITIVE LOGITS
    yntaxException
    0.61
    HostException
    0.60
    IntoConstraints
    0.52
    Personensuche
    0.51
    存于互联网档案馆
    0.50
    HomeAsUpEnabled
    0.47
     NSCoder
    0.45
    PerformLayout
    0.44
    󠁢
    0.44
    IndentedString
    0.42
    Activations Density 0.112%

    No Known Activations