© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 37548
    Prev
    Next
    INDEX
    Explanations

    references to gender, specifically female-related terms and mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    female

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Not in Any Lists

    No Comments

    Negative Logits
    inerary
    -0.65
    cuerdo
    -0.63
    itecture
    -0.59
    İstin
    -0.57
    oporosis
    -0.57
     Resolution
    -0.57
    cuits
    -0.57
    forestation
    -0.57
    pointments
    -0.56
    Gründe
    -0.56
    POSITIVE LOGITS
     female
    1.04
    Female
    0.96
     Female
    0.95
    female
    0.87
     FEMALE
    0.87
    FEMALE
    0.79
     male
    0.79
     Male
    0.73
     females
    0.73
    Male
    0.70
    Activations Density 0.020%

    No Known Activations