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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 173
    Prev
    Next
    INDEX
    Explanations

    references to women and their experiences

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

    references to women

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glio
    -0.56
    ilaire
    -0.54
    rax
    -0.53
    alaya
    -0.52
     hint
    -0.51
    aloo
    -0.51
    alos
    -0.50
    arsis
    -0.49
    gebied
    -0.49
     McIntosh
    -0.49
    POSITIVE LOGITS
     women
    1.77
    Women
    1.65
     Women
    1.59
    women
    1.55
     WOMEN
    1.45
    WOMEN
    1.41
     woman
    1.37
    Woman
    1.31
     Woman
    1.29
     mujeres
    1.24
    Activations Density 0.024%

    No Known Activations