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. 20-GEMMASCOPE-RES-16K
    6. 3238
    Prev
    Next
    INDEX
    Explanations

    keywords related to asynchronous programming patterns in JavaScript

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

    JavaScript array iteration/manipulation

    np_acts-logits-general · gemini-2.0-flash

    javascript promise callbacks

    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
     متعلقه
    -0.92
     समीक्षाओं
    -0.86
    LookAnd
    -0.84
     itſelf
    -0.78
     Houſe
    -0.75
     Reſ
    -0.75
     themſelves
    -0.75
     poffe
    -0.75
     myſelf
    -0.74
     greateſt
    -0.74
    POSITIVE LOGITS
    (
    0.56
    ((
    0.54
    (()
    0.51
     function
    0.49
    function
    0.47
     async
    0.45
     do
    0.42
    async
    0.42
    (()=>{
    0.41
     para
    0.41
    Activations Density 0.050%

    No Known Activations