Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7104
    Prev
    Next
    INDEX
    Explanations

    terminology related to race and ethnicity issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енча
    -0.53
    레이
    -0.47
    ir
    -0.47
     Վերցված
    -0.47
    ไหน
    -0.45
     inol
    -0.45
    doras
    -0.44
    ylvan
    -0.44
    を迎
    -0.43
     Mor
    -0.43
    POSITIVE LOGITS
     ethnic
    1.09
     racially
    1.04
     racial
    1.00
     Ethnic
    0.91
     ethnicity
    0.86
     Racial
    0.85
     minorities
    0.85
     AssemblyCulture
    0.80
    Ethnic
    0.79
     polaire
    0.78
    Activations Density 2.019%

    No Known Activations