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. 14253
    Prev
    Next
    INDEX
    Explanations

    references to specific books and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    •Literature
    references to specific books and their authors

    No Comments

    Negative Logits
    Datuak
    -0.66
     HasFactory
    -0.63
     betweenstory
    -0.58
    ArrowToggle
    -0.57
     bailando
    -0.54
    apimachinery
    -0.54
    featureID
    -0.54
     protoimpl
    -0.53
    ⓧ
    -0.52
    Sklici
    -0.52
    POSITIVE LOGITS
     book
    1.85
     books
    1.83
     Books
    1.65
     Book
    1.60
    books
    1.58
    Books
    1.55
    Book
    1.52
    book
    1.52
     reading
    1.50
     bookstores
    1.48
    Activations Density 0.784%

    No Known Activations