© 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. 11703
    Prev
    Next
    INDEX
    Explanations

    syntax elements typically associated with programming code

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

    Code with conditional statements ("if," "else," "elif")

    np_acts-logits-general · gemini-2.0-flash

    else and elif

    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
     betweenstory
    -0.54
    aphthalene
    -0.48
     Chwiliwch
    -0.48
     Мексичка
    -0.46
     parco
    -0.44
     souver
    -0.43
    startswith
    -0.41
    portál
    -0.41
     Repr
    -0.41
    Ведь
    -0.41
    POSITIVE LOGITS
     than
    0.97
     للاسماء
    0.97
     rather
    0.77
    rather
    0.73
    setVerticalGroup
    0.72
     ELSE
    0.72
     THAN
    0.72
    elsif
    0.69
    elif
    0.69
     아니라
    0.69
    Activations Density 0.094%

    No Known Activations