© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5549
    Prev
    Next
    INDEX
    Explanations

    references to Common Weakness Enumeration (CWE) identifiers and related programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tragedy
    -0.48
    entier
    -0.47
     dobre
    -0.45
     tuturor
    -0.44
     Internacional
    -0.43
     moda
    -0.43
    Flatten
    -0.42
     sát
    -0.42
    bard
    -0.41
     plucked
    -0.41
    POSITIVE LOGITS
    jspx
    7.14
    ftagPool
    2.45
    SourceChecksum
    1.69
    tagext
    1.39
    WireFormatLite
    1.21
     AssemblyCulture
    1.15
     jspb
    1.12
     autorytatywna
    1.10
     nahilalakip
    1.09
    ScopeManager
    1.09
    Activations Density 0.002%

    No Known Activations