© 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. 104854
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to discrimination and employee rights

    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
    agencies
    -0.37
     Agencies
    -0.35
     agencies
    -0.33
     capturar
    -0.33
    niños
    -0.33
     Trap
    -0.32
     ressemb
    -0.32
    record
    -0.31
     bait
    -0.31
     BN
    -0.31
    POSITIVE LOGITS
     ब्रेकडाउन
    0.69
     виправивши
    0.58
    oa̍t
    0.57
    下载附件
    0.55
    VYMaps
    0.54
    ngdoc
    0.54
    Meik
    0.54
     SwitchCompat
    0.53
    XmlAccessorType
    0.50
     nahilalakip
    0.50
    Activations Density 0.190%

    No Known Activations