© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 44598
    Prev
    Next
    INDEX
    Explanations

    references to ethnic groups and cultural identities

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

    Roma, boho, Bohemian, horse herd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     deportivas
    -0.38
     dieux
    -0.36
     sanitarias
    -0.36
    kül
    -0.36
     claras
    -0.36
     düşünü
    -0.35
     eléctricas
    -0.35
     mascarilla
    -0.35
     polaire
    -0.34
     masculinos
    -0.34
    POSITIVE LOGITS
     Gypsy
    1.03
     gypsy
    1.00
    ypsies
    0.98
    Gypsy
    0.92
     autorytatywna
    0.82
     Dust
    0.67
    ioutil
    0.65
     dust
    0.65
     disambiguazione
    0.64
     nomadic
    0.64
    Activations Density 0.006%

    No Known Activations