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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13007
    Prev
    Next
    INDEX
    Explanations

    specific mathematical or computational symbols and structures in the text

    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
     <>",
    -0.97
     oprot
    -0.78
    SharedDtor
    -0.72
    ErrUnexpectedEOF
    -0.66
    AntiForgeryToken
    -0.62
    DeleteBehavior
    -0.61
     AssemblyCulture
    -0.61
     MenuView
    -0.61
     newBuilder
    -0.60
     Paglinawan
    -0.60
    POSITIVE LOGITS
    toHave
    0.61
     "..\..\..\
    0.61
    irited
    0.61
     '@/
    0.61
    toContain
    0.58
    Orléans
    0.55
     /\.
    0.55
    ់
    0.54
     Auto
    0.54
    setViewName
    0.54
    Activations Density 0.319%

    No Known Activations