© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-16K
    11. 2112
    Prev
    Next
    INDEX
    Explanations

    programming and structural syntax elements in code

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

    Code or markup

    np_acts-logits-general · gemini-2.0-flash

    special characters in code or math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.44
    pyx
    -0.43
     bào
    -0.40
     Dostupné
    -0.40
     asht
    -0.40
     gere
    -0.39
    Uhr
    -0.39
     Kane
    -0.39
    Judi
    -0.39
     Exactos
    -0.39
    POSITIVE LOGITS
    SequentialGroup
    1.02
    complexContent
    0.64
    RuleContext
    0.60
     disambiguazione
    0.60
    MemoryWarning
    0.58
    AccessorTable
    0.57
    Autoritní
    0.56
     BoxDecoration
    0.54
    лтемелер
    0.53
    ViewFeatures
    0.53
    Activations Density 0.111%

    No Known Activations