© 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. 30-GEMMASCOPE-RES-16K
    11. 7560
    Prev
    Next
    INDEX
    Explanations

    patterns of repeated elements and specific keys in structured data

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

    Tokens followed by specific punctuation or capitalization

    np_acts-logits-general · gemini-2.0-flash

    repeated, singular, packed fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ੝
    -0.74
    
    -0.59
    ﮢ
    -0.57
    onOptions
    -0.57
    𖧹
    -0.57
    LEn
    -0.57
    ஥
    -0.56
    
    -0.55
    XmlAccessType
    -0.55
    logr
    -0.55
    POSITIVE LOGITS
     Economía
    0.51
     Italij
    0.50
     venganza
    0.47
     almohada
    0.45
    latego
    0.45
     actualidad
    0.45
     regalías
    0.45
     Simplemente
    0.45
     kaupung
    0.41
     chrétien
    0.41
    Activations Density 0.647%

    No Known Activations