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. 7413
    Prev
    Next
    INDEX
    Explanations

    specialized terminology or concepts associated with specific fields or disciplines

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

    Scientific or technical terminology appearing in formal documents like research papers, patents, or legal texts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     keseluruhan
    -0.40
     betweenstory
    -0.40
     שוליים
    -0.40
     cortesía
    -0.39
    alahkan
    -0.36
     hänen
    -0.36
     enquanto
    -0.34
     oposición
    -0.34
     mentre
    -0.34
    而
    -0.34
    POSITIVE LOGITS
    出版年
    0.65
     ſind
    0.62
    PyExc
    0.61
    astify
    0.59
     ब्रेकडाउन
    0.59
     चीज़ों
    0.56
    MessageOf
    0.54
     purpoſe
    0.54
    Чыганаклар
    0.53
     useAppContext
    0.53
    Activations Density 0.059%

    No Known Activations