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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1207
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" and references to notable individuals or titles

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

    names and titles associated with significant events or announcements

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

    voiced by

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AccessorTable
    -0.76
    Bronnen
    -0.58
    Externe
    -0.54
     liné
    -0.52
    Referenties
    -0.52
    MemoryWarning
    -0.51
    $_['
    -0.48
     firft
    -0.47
    VARI
    -0.47
    Clubs
    -0.47
    POSITIVE LOGITS
    BeginInit
    0.77
     AssemblyCompany
    0.73
    BeginContext
    0.64
    tagHelperRunner
    0.64
    MENAFN
    0.59
     Strait
    0.55
     Réponses
    0.53
    MeasureSpec
    0.53
    Diweddarwch
    0.53
    UnsafeEnabled
    0.51
    Activations Density 0.105%

    No Known Activations