© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3041
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their affiliations

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

    This neuron activates strongly on proper nouns and place names, particularly those that appear in citations, acknowledgments, and author attributions.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     שוליים
    -0.67
     snippetHide
    -0.67
     GenerationType
    -0.63
    MessageOf
    -0.63
    enderror
    -0.60
     EconPapers
    -0.60
    exitRule
    -0.58
    addCriterion
    -0.57
     ब्रेकडाउन
    -0.57
    verwijspagina
    -0.55
    POSITIVE LOGITS
    opinion
    0.37
     Strö
    0.35
     opin
    0.35
    Mind
    0.35
     belo
    0.34
    %^
    0.34
    ele
    0.33
     Mind
    0.33
     Todes
    0.33
     gros
    0.32
    Activations Density 0.312%

    No Known Activations