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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 9
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "await" and related asynchronous programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.78
    ization
    -0.63
     ['$
    -0.61
    ]-'
    -0.61
     constitution
    -0.57
    ca
    -0.55
     zvuky
    -0.53
     Abbe
    -0.52
    glEnd
    -0.52
     '(
    -0.51
    POSITIVE LOGITS
    await
    1.34
     await
    1.20
    Await
    1.07
     CreateTagHelper
    0.95
    tagHelperRunner
    0.94
    ValueStyle
    0.88
     Waits
    0.85
     asyncio
    0.81
    ranton
    0.80
    ruptedException
    0.79
    Activations Density 0.025%

    No Known Activations