© 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. 15-GEMMASCOPE-RES-16K
    11. 2895
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures, particularly those involved in file handling and data manipulation

    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
     lenker
    -0.96
     Efq
    -0.88
    Hochspringen
    -0.88
     propOrder
    -0.83
    IsContent
    -0.81
     ویکی‌پدیا
    -0.80
    المناصب
    -0.79
    AntiForgeryToken
    -0.78
     שוליים
    -0.78
    bootstrapcdn
    -0.78
    POSITIVE LOGITS
     -
    0.56
     +
    0.54
     >
    0.46
    ,
    0.46
    .
    0.45
     =
    0.40
    *
    0.39
     sign
    0.38
     +=
    0.37
     *
    0.37
    Activations Density 0.222%

    No Known Activations