© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12516
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding structures

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

    Code or calculations involving numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    program structure identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.44
    Nationalité
    -0.35
     Ensino
    -0.31
    getResultList
    -0.28
    setScene
    -0.28
     ProtoMessage
    -0.28
    fillText
    -0.28
    意
    -0.28
     στα
    -0.28
     ensued
    -0.27
    POSITIVE LOGITS
     >=",
    0.60
    
    0.58
     Biôgrafia
    0.58
    addCriterion
    0.57
    Ӕ
    0.56
    writeFieldEnd
    0.56
    Microkernel
    0.56
     bershka
    0.56
    rizona
    0.55
     FontFamily
    0.55
    Activations Density 0.455%

    No Known Activations