© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 512
    Prev
    Next
    INDEX
    Explanations

    string interpolation patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    template literals used for string interpolation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code snippets with interpolation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.75
    SharedDtor
    -0.68
    şiv
    -0.64
    mobileqq
    -0.59
    ARGS
    -0.58
    出版年
    -0.57
    Chico
    -0.55
    ist
    -0.55
    AsUp
    -0.54
     NSCoder
    -0.54
    POSITIVE LOGITS
    ChildScrollView
    0.76
    帖最后由
    0.70
    ably
    0.66
    HasForeignKey
    0.65
    )))),
    0.64
    nameof
    0.64
     satisfait
    0.60
    "",
    0.60
    doise
    0.60
    ۰۱
    0.59
    Activations Density 0.011%

    No Known Activations