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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 91593
    Prev
    Next
    INDEX
    Explanations

    terms related to feminism and feminist movements

    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
    EDEFAULT
    -0.58
     disambiguazione
    -0.52
    XtraGrid
    -0.52
     BorderSide
    -0.50
    astéroïdes
    -0.49
     Bridge
    -0.47
     Mysteries
    -0.47
    ﹧
    -0.47
    Santis
    -0.47
     Pike
    -0.47
    POSITIVE LOGITS
     feminist
    0.91
     feminism
    0.82
     Feminist
    0.78
     feminists
    0.72
     Feminism
    0.70
    femin
    0.67
    Femin
    0.60
     Femin
    0.59
     fémin
    0.57
     femin
    0.55
    Activations Density 0.002%

    No Known Activations