© 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. 24-GEMMASCOPE-RES-16K
    11. 5641
    Prev
    Next
    INDEX
    Explanations

    connections between geographical locations and borders

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

    Border, boundary, or perimeter

    np_acts-logits-general · gemini-2.0-flash

    spatial boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    หาย
    -0.40
    slidesToShow
    -0.38
     мәкал
    -0.37
     descomp
    -0.35
    fahan
    -0.35
     cyclisme
    -0.35
    huriyet
    -0.34
    ыгана
    -0.33
    retanto
    -0.33
    backward
    -0.32
    POSITIVE LOGITS
     border
    1.15
     boundary
    1.05
     Border
    0.95
     borders
    0.95
    Border
    0.88
     BORDER
    0.86
     Boundary
    0.85
    border
    0.84
    boundary
    0.84
     Borders
    0.80
    Activations Density 0.769%

    No Known Activations