© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105443
    Prev
    Next
    INDEX
    Explanations

    references to genes and healthcare professionals or patients

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    principalColumn
    -0.73
    ViewFeatures
    -0.65
    CodeAttribute
    -0.65
     ExecuteAsync
    -0.62
    WriteAttribute
    -0.59
    printStackTrace
    -0.58
    دانشنامهٔ
    -0.55
    XtraReports
    -0.54
    BeginContext
    -0.54
     ideal
    -0.50
    POSITIVE LOGITS
     valgt
    0.47
     nødvendig
    0.41
     jotka
    0.41
     antaranya
    0.39
    __":
    0.39
     forfatter
    0.38
     maquiagem
    0.38
     gekozen
    0.37
     uitgenodigd
    0.36
     irmã
    0.36
    Activations Density 0.099%

    No Known Activations