© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11670
    Prev
    Next
    INDEX
    Explanations

    references to male gender and related biological terms

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

    "male" and sex/gender

    np_acts-logits-general · gemini-2.0-flash

    male sterility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.79
     transférez
    -0.79
     Italijanski
    -0.78
     InputDecoration
    -0.76
    tagHelperRunner
    -0.76
    AndEndTag
    -0.73
    팎
    -0.73
     للاسماء
    -0.71
    protoimpl
    -0.70
    GraphicsUnit
    -0.70
    POSITIVE LOGITS
    volent
    1.04
     gender
    0.76
    vol
    0.55
     sex
    0.54
    MALE
    0.53
    volen
    0.52
     Male
    0.52
     av
    0.52
    gender
    0.51
    branche
    0.51
    Activations Density 0.147%

    No Known Activations