© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8452
    Prev
    Next
    INDEX
    Explanations

    references to women's identities and roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Totale
    -0.40
     transfieras
    -0.39
    inette
    -0.37
    razine
    -0.35
    liosis
    -0.35
     THEATRE
    -0.35
     WARS
    -0.35
     Pineda
    -0.35
    yung
    -0.34
     ulang
    -0.34
    POSITIVE LOGITS
    folk
    0.64
    Women
    0.63
    WOMEN
    0.62
     Men
    0.60
     Women
    0.60
     women
    0.60
     MEN
    0.57
    DotNetBar
    0.56
     men
    0.54
    Men
    0.54
    Activations Density 0.128%

    No Known Activations