Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10797
    Prev
    Next
    INDEX
    Explanations

    references to Asian populations and cultural elements

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

    Asian origin or cuisine

    np_acts-logits-general · gemini-2.0-flash

    Asian and Chinese people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >{@
    -0.45
    الحياه
    -0.41
    ⓘ
    -0.41
    קישורים
    -0.36
    endregion
    -0.35
    魔女
    -0.34
     Buc
    -0.34
    EditorBrowsable
    -0.33
     LOGGER
    -0.33
     UUID
    -0.33
    POSITIVE LOGITS
     Chinese
    1.52
     Asian
    1.47
     asiatique
    1.34
    Chinese
    1.34
     Asians
    1.31
    Asian
    1.30
     CHINESE
    1.30
     asian
    1.23
     asiática
    1.21
     chinese
    1.20
    Activations Density 0.512%

    No Known Activations