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. 14522
    Prev
    Next
    INDEX
    Explanations

    references to art-related organizations and their activities

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

    Follows certain words (Group, highly, platform, customers, as)

    np_acts-logits-general · gemini-2.0-flash

    explosive recommendations and events

    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
     iNdEx
    -0.71
    principalTable
    -0.66
    Datuak
    -0.65
    存于互联网档案馆
    -0.64
    Ótimo
    -0.64
    Geplaatst
    -0.63
     itſelf
    -0.63
    CELLANEOUS
    -0.63
    modelBuilder
    -0.62
     photolibrary
    -0.61
    POSITIVE LOGITS
     @"/
    0.55
     netizens
    0.54
     "
    0.48
     industry
    0.48
    KommentareTeilen
    0.47
    ["
    0.47
    _,
    0.46
    [_
    0.46
    seck
    0.45
     _
    0.44
    Activations Density 0.039%

    No Known Activations