© 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. 20-GEMMASCOPE-RES-16K
    11. 7832
    Prev
    Next
    INDEX
    Explanations

    references to African American demographics and culture

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

    "African" followed by "American"

    np_acts-logits-general · gemini-2.0-flash

    African American culture and demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.60
    BackStack
    -0.57
    WriteTagHelper
    -0.54
     indisponible
    -0.50
    ưỡng
    -0.50
     consultato
    -0.48
     Nip
    -0.47
    rani
    -0.46
    alga
    -0.46
     potrivit
    -0.46
    POSITIVE LOGITS
     American
    1.09
    American
    0.97
     Americans
    0.95
     AMERICAN
    0.94
     american
    0.89
    american
    0.85
     America
    0.84
    Americans
    0.80
     AMERIC
    0.78
    AMERICAN
    0.77
    Activations Density 0.118%

    No Known Activations