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. 8-GEMMASCOPE-RES-16K
    6. 11317
    Prev
    Next
    INDEX
    Explanations

    concepts related to asynchronous programming and promises in JavaScript

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.64
    MessageTagHelper
    -0.64
    bootstrapcdn
    -0.57
    település
    -0.56
    atov
    -0.56
    licherweise
    -0.56
    Rhestr
    -0.54
    astéroïdes
    -0.54
    appcompat
    -0.54
    发表于
    -0.53
    POSITIVE LOGITS
    rxjs
    1.09
    tableFuture
    1.08
    reactivex
    0.93
     Promise
    0.70
     Observable
    0.70
    Promise
    0.69
     BehaviorSubject
    0.64
    NewGuid
    0.63
    awaiter
    0.61
     promise
    0.57
    Activations Density 0.145%

    No Known Activations