© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12103
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical correlations in health-related research

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

    Floating point numbers close to zero

    np_acts-logits-general · gemini-2.0-flash

    correlation coefficients and p-values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     للمعارف
    -0.79
     hefyd
    -0.49
    anskje
    -0.46
    hoga
    -0.46
     mandatario
    -0.45
    aliyet
    -0.45
    ViewImports
    -0.42
    eclampsia
    -0.42
    anine
    -0.42
     abitanti
    -0.41
    POSITIVE LOGITS
    unhofer
    0.66
    #
    0.60
    ">//
    0.57
    ThroughAttribute
    0.57
    omentos
    0.55
    fVar
    0.54
     getProperty
    0.54
    rungsseite
    0.54
    weetened
    0.53
    ConstraintMaker
    0.53
    Activations Density 0.455%

    No Known Activations