© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2819
    Prev
    Next
    INDEX
    Explanations

    factors that explain variations or patterns related to health and behavior in populations

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

    explanation or reason

    np_acts-logits-general · gemini-2.0-flash

    explaining reasons why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.35
    !*\
    -0.31
     par
    -0.31
    borrow
    -0.31
     impli
    -0.31
     pstmt
    -0.31
    Impact
    -0.30
     спаса
    -0.30
     специально
    -0.30
    ukka
    -0.30
    POSITIVE LOGITS
    之所以
    0.82
     why
    0.81
     varför
    0.77
     hvorfor
    0.77
     mengapa
    0.75
     dlaczego
    0.75
     success
    0.75
     successes
    0.74
     succès
    0.71
     discrepancy
    0.69
    Activations Density 1.038%

    No Known Activations