© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 81336
    Prev
    Next
    INDEX
    Explanations

    names and identifiers related to individuals and cases in legal contexts

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

    legal citations and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    GEBURTSDATUM
    -0.69
    styleType
    -0.60
     noDo
    -0.58
    WebVitals
    -0.57
     betweenstory
    -0.56
    setupUi
    -0.55
    ThemeOverlay
    -0.54
    NameInMap
    -0.53
    kloped
    -0.52
     Biôgrafia
    -0.51
    POSITIVE LOGITS
    Personensuche
    0.39
    
    0.39
     Вікі
    0.37
     الحره
    0.36
    cwd
    0.35
    ModelSerializer
    0.33
     bew
    0.32
     franc
    0.32
     tro
    0.31
    houette
    0.31
    Activations Density 0.023%

    No Known Activations