© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10349
    Prev
    Next
    INDEX
    Explanations

    components related to programming syntax, particularly for variable declarations and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.80
    webElement
    -0.80
    DeleteBehavior
    -0.67
    CppCodeGen
    -0.63
    CloseOperation
    -0.62
    featureID
    -0.61
     ISNI
    -0.60
    Pranala
    -0.59
     xlink
    -0.59
     Tij
    -0.59
    POSITIVE LOGITS
     paramInt
    0.86
     AssemblyProduct
    0.69
    AppMethodBeat
    0.69
    isNameExpr
    0.63
     يتيمه
    0.62
     paramString
    0.58
    Билгалдахарш
    0.56
     تانيه
    0.55
     opportunities
    0.53
    jsdelivr
    0.52
    Activations Density 0.081%

    No Known Activations