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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1554
    Prev
    Next
    INDEX
    Explanations

    mentions of "men" and references to masculinity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.66
    ThroughAttribute
    -0.64
    FunctionFlags
    -0.63
    MLLoader
    -0.56
    enderror
    -0.54
     ModelExpression
    -0.53
    عرِّف
    -0.52
     EconPapers
    -0.51
    CodeAttribute
    -0.50
    ########.
    -0.50
    POSITIVE LOGITS
    agerie
    0.51
    WOMEN
    0.47
     WOMEN
    0.45
    Women
    0.44
     Women
    0.41
     women
    0.41
     mujeres
    0.39
     karet
    0.39
     Men
    0.39
    iscus
    0.38
    Activations Density 0.125%

    No Known Activations