© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5544
    Prev
    Next
    INDEX
    Explanations

    chemical terms and compounds related to medical or scientific processes

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

    Chemical compounds or formulas

    np_acts-logits-general · gemini-2.0-flash

    amines, amides, or sulfur compounds

    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
    ⓧ
    -0.80
     مشين
    -0.78
    ValueStyle
    -0.73
    SuppressLint
    -0.66
     apothe
    -0.65
     antenn
    -0.62
    localctx
    -0.62
     autorytatywna
    -0.60
    Tembelea
    -0.60
    Obrázky
    -0.59
    POSITIVE LOGITS
    LayoutStyle
    0.60
    essi
    0.59
     α
    0.58
     triste
    0.56
     것을
    0.56
    lino
    0.55
     iconos
    0.54
     perde
    0.54
     Paglinawan
    0.54
    گاب
    0.52
    Activations Density 1.711%

    No Known Activations