© 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. 24-GEMMASCOPE-RES-16K
    11. 12470
    Prev
    Next
    INDEX
    Explanations

    strong phrases indicating threats and conflicts involving rulers and empires

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

    Follows "she"

    np_acts-logits-general · gemini-2.0-flash

    she told, mathmathcal

    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
     "
    -0.29
     relevant
    -0.29
     regardless
    -0.27
    wijs
    -0.27
    >({
    -0.26
    adaptiveStyles
    -0.26
     beings
    -0.25
     Weisheit
    -0.25
     cabe
    -0.25
     through
    -0.24
    POSITIVE LOGITS
    RegressionTest
    0.79
    parsedMessage
    0.75
     ویکی‌پدی
    0.75
    𐑥
    0.66
     queſto
    0.66
     GoogleContinue
    0.65
     betweenstory
    0.65
    ſammen
    0.65
    CrossRef
    0.65
    ScopeManager
    0.64
    Activations Density 0.007%

    No Known Activations