© 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. 15-GEMMASCOPE-RES-16K
    11. 1893
    Prev
    Next
    INDEX
    Explanations

    syntactic structures within code, particularly identifying brackets and closing statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.62
     surla
    -0.58
    cerpt
    -0.56
    setViewportView
    -0.55
    LookAnd
    -0.54
     recta
    -0.53
     Administrativna
    -0.52
    transQ
    -0.51
     Rounds
    -0.49
    centiles
    -0.49
    POSITIVE LOGITS
     yrity
    0.47
     tarvit
    0.45
    archiviato
    0.41
    featureID
    0.41
    iNdEx
    0.40
     potřeb
    0.40
     whether
    0.39
     voorkomen
    0.39
     twij
    0.39
     bedrijven
    0.39
    Activations Density 0.110%

    No Known Activations