© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2964
    Prev
    Next
    INDEX
    Explanations

    mentions of agricultural practices and health-related interventions associated with vitamin and nutrient supplementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.55
     članak
    -0.50
    EnableWeb
    -0.47
    rungsseite
    -0.47
    Tembelea
    -0.46
    InSection
    -0.45
    istoitu
    -0.45
    ConstraintMaker
    -0.44
    QRect
    -0.43
     vœ
    -0.43
    POSITIVE LOGITS
    endpush
    0.42
    DockStyle
    0.40
     shopping
    0.36
     commerce
    0.35
     remittance
    0.35
     vixion
    0.35
     remittances
    0.34
    全ての
    0.34
     EVERY
    0.34
    المناصب
    0.33
    Activations Density 0.679%

    No Known Activations