© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3763
    Prev
    Next
    INDEX
    Explanations

    the word "quite" and evaluate its intensity in various contexts

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

    intensifying adverbs modifying following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    DebuggerNonUser
    -0.80
     onCancelled
    -0.66
     vapormax
    -0.63
    참고
    -0.62
    Portale
    -0.62
    Hentet
    -0.61
    Referanser
    -0.61
    InputBorder
    -0.59
    ГЛА
    -0.57
    fois
    -0.57
    POSITIVE LOGITS
     fewer
    0.72
     some
    0.65
     varying
    0.60
    Izvori
    0.60
     little
    0.60
     what
    0.57
     everything
    0.56
     meaningful
    0.53
    égalité
    0.53
    úmer
    0.52
    Activations Density 0.180%

    No Known Activations