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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10144
    Prev
    Next
    INDEX
    Explanations

    references to delegate patterns and associated functionalities in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsxFileName
    -0.87
    parsedMessage
    -0.85
    +#+#
    -0.84
     Aram
    -0.82
     Gies
    -0.81
    jstor
    -0.80
    extAlignment
    -0.77
     وتسجيلات
    -0.77
     Chry
    -0.76
    dotenv
    -0.76
    POSITIVE LOGITS
     delegate
    2.27
     Delegate
    2.06
    Delegate
    2.00
    delegate
    2.00
     delegates
    1.93
     Delegates
    1.84
    deleg
    1.83
    Dele
    1.62
     delegated
    1.48
     Deleg
    1.44
    Activations Density 0.068%

    No Known Activations