© 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. 20-GEMMASCOPE-RES-16K
    11. 10482
    Prev
    Next
    INDEX
    Explanations

    function definitions and variable manipulations in code

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

    C/C++ code syntax and operators

    np_acts-logits-general · gemini-2.0-flash

    bitwise operators and punctuation

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     IndexPath
    -0.48
     balance
    -0.47
     Tand
    -0.46
    offic
    -0.44
     তারিখ
    -0.43
    ALSO
    -0.42
     Hex
    -0.42
    ictus
    -0.41
    wakilan
    -0.41
     kone
    -0.41
    POSITIVE LOGITS
     Normdatei
    0.78
     وتسجيلات
    0.71
    ItemBackground
    0.65
     cherchés
    0.63
    BeginContext
    0.62
    elemField
    0.61
    IsContent
    0.60
    
    0.58
    TagMode
    0.57
    WireFormatLite
    0.57
    Activations Density 0.578%

    No Known Activations