© 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. 15-GEMMASCOPE-RES-16K
    11. 8223
    Prev
    Next
    INDEX
    Explanations

    references to methods or attributes in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.43
    ')[
    -0.42
    are
    -0.39
    ")[
    -0.37
     vai
    -0.37
    ARE
    -0.37
     partida
    -0.36
    {{
    -0.35
     duy
    -0.34
     Are
    -0.34
    POSITIVE LOGITS
    GHIJKLM
    0.85
    GIVEREF
    0.82
    WebServlet
    0.80
    Hochspringen
    0.79
    脚注の使い方
    0.76
    XmlAccessorType
    0.75
    ParallelGroup
    0.72
     AssemblyCompany
    0.72
     EconPapers
    0.71
    ExtendWith
    0.70
    Activations Density 0.656%

    No Known Activations