© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3258
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations, names, and titles in various contexts

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

    References or citations

    np_acts-logits-general · gemini-2.0-flash

    place names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ValueStyle
    -0.77
    RenderAtEndOf
    -0.70
    FieldBuilder
    -0.64
     للاسماء
    -0.63
    rungsseite
    -0.63
     ***!
    -0.62
    setVerticalGroup
    -0.62
     مرئيه
    -0.60
     ISNI
    -0.59
     ModelExpression
    -0.59
    POSITIVE LOGITS
    ™.
    0.79
    ®.
    0.66
    -------
    0.59
    ®:
    0.58
    Jäh
    0.58
    ™,
    0.56
     Etrus
    0.54
    Jährige
    0.54
    ℠
    0.52
     .
    0.52
    Activations Density 0.845%

    No Known Activations