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. 20-GEMMASCOPE-RES-131K
    6. 70688
    Prev
    Next
    INDEX
    Explanations

    names and terms related to martial arts or specific techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    mbggenerated
    -0.66
    quelles
    -0.58
     Grüsse
    -0.54
    NESDAY
    -0.54
    psons
    -0.52
    ListModule
    -0.52
    iſh
    -0.50
    kloped
    -0.49
     ویکی‌پدی
    -0.49
     appuntamento
    -0.49
    POSITIVE LOGITS
    ai
    0.94
    Gai
    0.79
    Ai
    0.79
    Lai
    0.77
    AI
    0.77
     Lai
    0.76
     Rai
    0.75
     Gai
    0.74
    mai
    0.73
    tai
    0.72
    Activations Density 0.037%

    No Known Activations