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
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23132
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions of gender, specifically references to "men" and "women."

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @bcywinski

    references to women and girls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubscribe
    -0.41
    ↴
    -0.39
     klara
    -0.38
    Check
    -0.38
    oros
    -0.37
    Crash
    -0.36
    Pug
    -0.36
    Qualified
    -0.35
    tunnel
    -0.35
    Newspaper
    -0.35
    POSITIVE LOGITS
     women
    0.82
     female
    0.74
    PreferredItem
    0.73
     woman
    0.72
     females
    0.68
     férfi
    0.64
     feminine
    0.64
    ValueStyle
    0.63
     ladies
    0.63
     male
    0.63
    Activations Density 0.068%

    No Known Activations