© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14587
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements typically used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    cèse
    -0.62
     estekak
    -0.60
     ͡°
    -0.58
     AssemblyProduct
    -0.56
    addContainerGap
    -0.56
     مشين
    -0.53
    enumi
    -0.53
    艋
    -0.51
    ]='\
    -0.51
     BoxFit
    -0.50
    POSITIVE LOGITS
     uſed
    0.56
     Stell
    0.55
     becauſe
    0.54
     skak
    0.54
     Beine
    0.53
     Aner
    0.53
    WebMethod
    0.52
    AddHtmlAttribute
    0.51
    Pautan
    0.51
     Vedi
    0.50
    Activations Density 0.170%

    No Known Activations