© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 37995
    Prev
    Next
    INDEX
    Explanations

    code syntax and markup related to API documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giảng
    -0.56
    XtraBars
    -0.50
     Fant
    -0.48
     ridu
    -0.47
    פ
    -0.47
     inf
    -0.46
     trời
    -0.46
     view
    -0.46
     Easton
    -0.45
    tite
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    2.39
    __);
    1.74
     فريبيس
    1.39
    forRoot
    1.20
     **)
    1.15
    CloseOperation
    1.05
    IVEREF
    1.05
     estekak
    1.05
    thesis
    0.98
    ":"",
    0.96
    Activations Density 0.000%

    No Known Activations