© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10759
    Prev
    Next
    INDEX
    Explanations

    references to women, particularly in the context of sports and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.96
    ustimmung
    -0.91
    ScopeManager
    -0.90
    principalTable
    -0.88
    Vidite
    -0.85
     myſelf
    -0.82
    ########.
    -0.81
    TypedDataSet
    -0.81
    WebElementEntity
    -0.80
     ErrInvalid
    -0.80
    POSITIVE LOGITS
     womens
    0.74
    s
    0.72
     Mens
    0.67
    omens
    0.66
    womens
    0.65
     Womens
    0.64
     mens
    0.64
     
    0.63
    mens
    0.59
    Mens
    0.58
    Activations Density 0.124%

    No Known Activations