© 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. 2-GEMMASCOPE-RES-16K
    11. 3935
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "book" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.82
     Efq
    -0.81
    posedge
    -0.81
     Majefty
    -0.79
    LayoutConstraint
    -0.79
    nabis
    -0.78
     ſeveral
    -0.74
     Mitar
    -0.74
    addPreferredGap
    -0.74
     Weiden
    -0.74
    POSITIVE LOGITS
     Book
    3.62
     book
    3.62
    Book
    3.46
    book
    3.44
     BOOK
    3.19
    BOOK
    3.07
     books
    2.91
    books
    2.83
     Books
    2.65
    Books
    2.52
    Activations Density 0.051%

    No Known Activations