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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1830
    Prev
    Next
    INDEX
    Explanations

    keywords and syntax related to error handling and exceptions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.66
    essoal
    -0.57
     الاطلاع
    -0.57
    出版年
    -0.57
    PerformLayout
    -0.55
    исленность
    -0.53
    TagMode
    -0.49
    transQ
    -0.49
     referenties
    -0.48
     Woodruff
    -0.47
    POSITIVE LOGITS
     throwing
    0.83
     thrown
    0.81
     throws
    0.80
     throw
    0.78
     gracefully
    0.77
     caught
    0.76
     Throw
    0.75
    抛
    0.75
     raised
    0.75
    Throw
    0.74
    Activations Density 0.760%

    No Known Activations