© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 90707
    Prev
    Next
    INDEX
    Explanations

    concepts related to multiculturalism and cultural sensitivity

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

    cultural sensitivity and multicultural strategies

    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
    DockStyle
    -0.82
    WebVitals
    -0.72
    expandindo
    -0.69
    CloseOperation
    -0.66
    Życiorys
    -0.65
    __':
    -0.62
    __":
    -0.62
     հղումներ
    -0.61
    NUMX
    -0.59
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
     cultures
    0.65
     intercultural
    0.57
     Cultures
    0.56
     culture
    0.54
     cultural
    0.53
     Cultural
    0.47
     Culture
    0.47
     culturas
    0.46
     countries
    0.46
    cultures
    0.45
    Activations Density 0.026%

    No Known Activations