© 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. 1917
    Prev
    Next
    INDEX
    Explanations

    complex mathematical formulations and references to specific proofs or conditions

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

    preceding "to" or "in"

    np_acts-logits-general · gemini-2.0-flash

    state or existence

    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
     للمعارف
    -0.80
    parsedMessage
    -0.63
     disambiguazione
    -0.62
     للاسماء
    -0.60
    oredCriteria
    -0.59
    Rüyada
    -0.59
    ViewImports
    -0.58
     ExecuteAsync
    -0.55
     resourceCulture
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    POSITIVE LOGITS
     accordingly
    0.79
     therefore
    0.65
    はその
    0.61
     therefor
    0.60
    Accordingly
    0.58
    Therefore
    0.57
     anyway
    0.57
    そういった
    0.55
    therefore
    0.54
     Accordingly
    0.52
    Activations Density 1.204%

    No Known Activations