© 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. 3691
    Prev
    Next
    INDEX
    Explanations

    code structure and class definitions in programming

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

    Code related to utilities or functions

    np_acts-logits-general · gemini-2.0-flash

    utility code

    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
     BoxDecoration
    -0.57
     sièges
    -0.53
    PositiveButton
    -0.51
     faibles
    -0.50
     exemplaires
    -0.46
    Hentet
    -0.46
    ypress
    -0.46
    accepte
    -0.46
    ্প
    -0.46
     Verpflichtung
    -0.46
    POSITIVE LOGITS
     utilities
    1.14
     utility
    1.11
     utils
    1.08
    utility
    1.02
     constants
    1.00
     Utility
    1.00
    utilities
    1.00
    util
    0.99
    utils
    0.99
     Utilities
    0.98
    Activations Density 0.169%

    No Known Activations