© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9680
    Prev
    Next
    INDEX
    Explanations

    terms related to racing and its intersection with ethnicity and race issues

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

    the word "race" in various contexts.

    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
    一点
    -0.35
     douce
    -0.33
     sweet
    -0.33
     ი
    -0.31
     Shield
    -0.30
     ต่อ
    -0.30
    ximadamente
    -0.29
    症
    -0.29
     Tamp
    -0.29
     Sweet
    -0.29
    POSITIVE LOGITS
     Race
    0.94
    Race
    0.92
     RACE
    0.88
     race
    0.87
    race
    0.80
    Rac
    0.75
    RACE
    0.74
     Races
    0.72
    MigrationBuilder
    0.72
     racer
    0.71
    Activations Density 0.122%

    No Known Activations