© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1615
    Prev
    Next
    INDEX
    Explanations

    references to books and related concepts

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

    "book" or "books."

    np_acts-logits-general · gemini-2.0-flash

    book followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemId
    -0.62
    ValueStyle
    -0.61
    UserScript
    -0.54
    cloudflare
    -0.53
    olesome
    -0.53
    sena
    -0.53
    rile
    -0.52
    addPreferredGap
    -0.51
    iyle
    -0.50
    LayoutConstraint
    -0.50
    POSITIVE LOGITS
     books
    1.28
    books
    1.20
     Books
    1.10
     Book
    1.08
    Books
    1.06
     book
    1.06
     BOOK
    1.03
    BOOK
    1.01
     Booker
    0.99
    book
    0.93
    Activations Density 0.138%

    No Known Activations