© 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. 3671
    Prev
    Next
    INDEX
    Explanations

    closing braces and catch blocks in code

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

    Code within `catch` and `finally` blocks

    np_acts-logits-general · gemini-2.0-flash

    try-catch-finally blocks

    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
     AssemblyCulture
    -1.06
    elif
    -0.90
     elif
    -0.86
     linkovi
    -0.83
     other
    -0.78
     andere
    -0.75
     Otras
    -0.75
     Efq
    -0.72
     ELSE
    -0.71
    other
    -0.70
    POSITIVE LOGITS
    finally
    1.65
     finally
    1.61
     Finally
    1.35
    Finally
    1.32
     FINALLY
    1.10
     finalmente
    1.08
     наконец
    1.01
    Finalmente
    0.98
     enfin
    0.97
     akhirnya
    0.96
    Activations Density 0.024%

    No Known Activations