© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    mentions of command-line arguments

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

    Java `main` method arguments

    np_acts-logits-general · gemini-2.0-flash

    main method signature

    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
     Italijanski
    -0.85
    بوابة
    -0.83
    webElementXpaths
    -0.80
     ſeveral
    -0.80
     nahilalakip
    -0.79
     laſt
    -0.76
    Enllaces
    -0.75
    parsedMessage
    -0.72
     IActionResult
    -0.71
    Jereo
    -0.70
    POSITIVE LOGITS
     args
    0.99
    args
    0.76
     Args
    0.63
    Args
    0.62
     MainAxisSize
    0.58
    UMENTS
    0.56
     argparse
    0.56
     Rah
    0.55
    omenti
    0.55
     Kel
    0.51
    Activations Density 0.035%

    No Known Activations