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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1102
    Prev
    Next
    INDEX
    Explanations

    references to Chinese or Japanese identity or culture

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

    Chinese and Japanese nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wymiar
    -0.63
     tričko
    -0.56
    awtextra
    -0.54
    вгений
    -0.54
    ltä
    -0.53
     kapturem
    -0.53
     Nachmittag
    -0.52
     sentiers
    -0.52
    fromnode
    -0.52
     torebka
    -0.52
    POSITIVE LOGITS
     Chinese
    0.68
     Japanese
    0.65
    Chinese
    0.59
    s
    0.58
    Japanese
    0.57
    inese
    0.57
     Swiss
    0.56
     Irish
    0.56
    ese
    0.55
     оригіналу
    0.55
    Activations Density 0.030%

    No Known Activations