© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    programming and code-related syntax elements

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

    Lines starting with "require"

    np_acts-logits-general · gemini-2.0-flash

    require statements

    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
    ConstraintMaker
    -0.60
    TagMode
    -0.59
    Hochspringen
    -0.57
     Infórmanos
    -0.56
    новништво
    -0.56
     detailsLots
    -0.54
    PullParser
    -0.52
     disambiguazione
    -0.50
     JpaRepository
    -0.49
    EDEFAULT
    -0.48
    POSITIVE LOGITS
     ausz
    0.47
    DIS
    0.41
    ьажоргаш
    0.40
    cannot
    0.40
     Mandatory
    0.39
    MOD
    0.39
    Toxic
    0.38
    DIV
    0.38
    Due
    0.38
    BAL
    0.38
    Activations Density 0.837%

    No Known Activations