Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67543
    Prev
    Next
    INDEX
    Explanations

    references and discussions related to gender, specifically focusing on women's roles and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     onCreateView
    -0.50
    tagHelperRunner
    -0.48
     navideña
    -0.45
    ódios
    -0.43
    ↴
    -0.40
     współpra
    -0.39
    ustre
    -0.38
     notified
    -0.38
     geçir
    -0.37
    couvrez
    -0.37
    POSITIVE LOGITS
     women
    1.00
    Women
    0.91
     female
    0.89
    women
    0.88
     Women
    0.88
     feminine
    0.88
     females
    0.84
    Frauen
    0.84
     gender
    0.82
     ladies
    0.82
    Activations Density 0.086%

    No Known Activations