© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9702
    Prev
    Next
    INDEX
    Explanations

    programming or coding-related terms, especially those indicating errors and system functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     OFDb
    -0.39
     المعيارى
    -0.31
    ที่ยว
    -0.31
     kolei
    -0.31
     Krie
    -0.30
    wijl
    -0.29
     Kerja
    -0.29
    ерез
    -0.29
     cifra
    -0.28
     ModelExpression
    -0.28
    POSITIVE LOGITS
    الحياه
    0.57
     also
    0.56
     també
    0.55
    Télécharger
    0.52
    loride
    0.51
     أيضا
    0.51
    transQ
    0.49
    ついでに
    0.48
     ALSO
    0.47
    InjectAttribute
    0.47
    Activations Density 0.592%

    No Known Activations