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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 513
    Prev
    Next
    INDEX
    Explanations

    code-related directives and commands for conditional checks and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.64
    HandleFunc
    -0.55
     RouterModule
    -0.55
    KommentareTeilen
    -0.55
    المناصب
    -0.52
    CreateMap
    -0.50
    addCriterion
    -0.49
     {?>
    -0.49
    Erstellt
    -0.48
    exitRule
    -0.48
    POSITIVE LOGITS
    RTLD
    0.67
    ConfigureAwait
    0.63
     שוליים
    0.60
    enterian
    0.60
    帖最后由
    0.58
    옵
    0.58
    hloromethane
    0.57
    ErrorListener
    0.56
    tonsoft
    0.56
    GraphicsUnit
    0.55
    Activations Density 0.237%

    No Known Activations