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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2889
    Prev
    Next
    INDEX
    Explanations

    references to foundational concepts and scientific terminology, particularly regarding acids and foundational principles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.63
     informée
    -0.63
     Administrativna
    -0.61
     الرياضيه
    -0.59
    PerformLayout
    -0.56
    省市镇
    -0.54
    يميديا
    -0.54
    كويكب
    -0.52
    httphttps
    -0.52
     poveznice
    -0.52
    POSITIVE LOGITS
     trades
    0.61
     trade
    0.57
    Trade
    0.52
     Trade
    0.52
     Trades
    0.50
     foundation
    0.49
    Trades
    0.49
    TRADE
    0.47
    trades
    0.46
     trading
    0.45
    Activations Density 0.210%

    No Known Activations