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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8208
    Prev
    Next
    INDEX
    Explanations

    numerical data or tabular representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     ModelExpression
    -0.71
    AddTagHelper
    -0.62
    balleur
    -0.55
    ьаж
    -0.53
    bitField
    -0.52
     <=",
    -0.48
    addCriterion
    -0.48
    VIAF
    -0.47
    hyrchwyd
    -0.47
    +#+
    -0.47
    POSITIVE LOGITS
    ChildScrollView
    0.71
     pages
    0.66
     page
    0.64
     Page
    0.60
    Page
    0.57
    pages
    0.52
     sheet
    0.51
    page
    0.50
    页面
    0.50
     pagine
    0.49
    Activations Density 0.618%

    No Known Activations