© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14912
    Prev
    Next
    INDEX
    Explanations

    patterns related to function definitions and method calls in programming code

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

    Milliseconds or time values in code

    np_acts-logits-general · gemini-2.0-flash

    milliseconds as duration

    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
     catch
    -2.11
     catching
    -1.95
     catches
    -1.89
     Catch
    -1.87
    catch
    -1.85
     caught
    -1.82
     CATCH
    -1.69
    caught
    -1.69
    Catch
    -1.63
    catching
    -1.57
    POSITIVE LOGITS
     endregion
    0.49
     Adkins
    0.47
     kasarigan
    0.43
    AutoresizingMask
    0.39
    saco
    0.39
    ENSA
    0.38
    íncia
    0.37
    setCancelable
    0.36
     governador
    0.36
    ramide
    0.36
    Activations Density 0.150%

    No Known Activations