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. 20-GEMMASCOPE-RES-16K
    6. 12638
    Prev
    Next
    INDEX
    Explanations

    JavaScript syntax related to asynchronous functions and Promises

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

    Code that uses "await"

    np_acts-logits-general · gemini-2.0-flash

    Gumball awaits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    +:+
    -0.51
    
    -0.47
    è
    -0.47
    others
    -0.46
    igneurs
    -0.45
     oly
    -0.43
    sometimes
    -0.43
     Vind
    -0.43
    CRIP
    -0.43
    especially
    -0.42
    POSITIVE LOGITS
     await
    2.83
    await
    2.78
     awaits
    1.79
     awaiting
    1.76
     awaited
    1.59
     waiting
    1.47
     wait
    1.42
    Await
    1.29
     Waiting
    1.27
     waits
    1.24
    Activations Density 0.059%

    No Known Activations