© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13721
    Prev
    Next
    INDEX
    Explanations

    keywords related to gender and ethnicity

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

    proper nouns and named entities, particularly names of people, places, and organizations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.61
    ים
    -0.95
    ات
    -0.70
    sted
    -0.66
    ς
    -0.64
    URLException
    -0.64
    pherals
    -0.61
    bidities
    -0.60
    stanbul
    -0.57
    ships
    -0.57
    POSITIVE LOGITS
    <bos>
    0.76
    𝓮
    0.58
    𝓵
    0.57
    o
    0.57
    𝓲
    0.56
    𝓭
    0.54
    er
    0.52
    𝓸
    0.52
    𝓱
    0.50
    𝓴
    0.50
    Activations Density 1.995%

    No Known Activations