© 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. 5-GEMMASCOPE-RES-16K
    11. 4950
    Prev
    Next
    INDEX
    Explanations

    terms related to discrimination and inequality based on various characteristics such as race, color, religion, sex, and other protected classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.87
     estekak
    -0.78
    DockStyle
    -0.66
    migrationBuilder
    -0.65
     Sandstone
    -0.64
    fohlen
    -0.63
    Искәрмәләр
    -0.63
    //});
    -0.61
    RenderAtEndOf
    -0.61
     للمعارف
    -0.61
    POSITIVE LOGITS
     ethnicity
    0.72
     gender
    0.68
     nationality
    0.66
     interests
    0.63
     ethnic
    0.63
     status
    0.62
     interesses
    0.60
    gender
    0.59
     Ethnicity
    0.59
     Nationality
    0.59
    Activations Density 0.447%

    No Known Activations