© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    individual elements and components related to programming structure

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

    Code-related tokens and symbols

    np_acts-logits-general · gemini-2.0-flash

    optional Int, show progress

    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
    .
    -0.58
     rumahnya
    -0.46
    ().
    -0.46
     lemah
    -0.45
    切って
    -0.43
     augmenté
    -0.42
    moderator
    -0.41
     extérieures
    -0.41
     jorden
    -0.40
    kese
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    1.29
    :✨
    0.95
     Anſ
    0.93
    tagHelperRunner
    0.92
     Diſ
    0.91
     Theſe
    0.90
     protoimpl
    0.87
     typelib
    0.85
     Inſ
    0.84
     Roskov
    0.83
    Activations Density 0.222%

    No Known Activations