© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8249
    Prev
    Next
    INDEX
    Explanations

    gender-related terms and differences in medical context

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

    gender and sex

    np_acts-logits-general · gemini-2.0-flash

    male and female distinctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    versaire
    -0.47
    verwijspagina
    -0.46
    SuccessListener
    -0.46
    ViewFeatures
    -0.45
    laşı
    -0.44
     صوتيه
    -0.44
    IVEREF
    -0.42
     pageContext
    -0.42
     disponibilités
    -0.41
    Cousin
    -0.40
    POSITIVE LOGITS
     female
    2.21
     male
    1.97
     females
    1.97
     Female
    1.94
     women
    1.88
    Female
    1.87
    female
    1.82
     gender
    1.78
     Females
    1.74
     FEMALE
    1.73
    Activations Density 0.473%

    No Known Activations