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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14657
    Prev
    Next
    INDEX
    Explanations

    elements related to books and their content

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

    books or printed materials

    np_acts-logits-general · gemini-2.0-flash

    book pages and binding

    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
    +#+#
    -0.61
    ContextHolder
    -0.59
    LikeLiked
    -0.57
    writerow
    -0.56
    setupUi
    -0.55
    OGND
    -0.55
    ThemeOverlay
    -0.55
     jLabel
    -0.54
    ActivityCompat
    -0.54
    eterminate
    -0.53
    POSITIVE LOGITS
     pages
    1.09
     printed
    1.04
     booklet
    0.99
     binding
    0.95
     binder
    0.95
     hardcover
    0.94
     paperback
    0.93
     book
    0.92
     booklets
    0.91
     binders
    0.89
    Activations Density 0.272%

    No Known Activations