© 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. 9-GEMMASCOPE-RES-131K
    11. 42640
    Prev
    Next
    INDEX
    Explanations

    words and terms related to specific ethnic or cultural identities

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

    ethnic groups and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.56
     للاسماء
    -0.50
    )];
    -0.45
    expandindo
    -0.44
    )}.
    -0.43
     ujednoznacz
    -0.42
    gradation
    -0.42
     orbs
    -0.40
    énario
    -0.40
     preocupes
    -0.39
    POSITIVE LOGITS
     Yoruba
    0.63
     Kurdish
    0.63
     Basque
    0.58
     Eskimo
    0.57
     Zulu
    0.57
     Navajo
    0.56
     Igbo
    0.55
     Tamil
    0.55
     Maori
    0.54
    Tamil
    0.54
    Activations Density 0.029%

    No Known Activations