© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific formatting within code or programming text

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

    Code snippets and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code snippets and programmatic terms

    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
     '\\;'
    -0.86
     betweenstory
    -0.86
     препратки
    -0.80
     disambiguazione
    -0.79
    esez
    -0.77
     kasarigan
    -0.73
    InputBorder
    -0.70
    جمعیت
    -0.70
     surla
    -0.69
    UnsafeEnabled
    -0.69
    POSITIVE LOGITS
    (&:
    0.54
     Coarse
    0.50
    ollectionView
    0.50
     konge
    0.50
    ontal
    0.49
    ".$_
    0.48
     quede
    0.47
     saveiro
    0.47
     Thumbnails
    0.47
    ALLED
    0.46
    Activations Density 0.082%

    No Known Activations