© 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. 5372
    Prev
    Next
    INDEX
    Explanations

    syntax tokens indicative of programming structure

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

    Code, especially with brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing code 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
     présidenti
    -0.60
     quelcon
    -0.58
     sicura
    -0.57
     hjemme
    -0.56
     normaux
    -0.54
     extérieurs
    -0.54
     détach
    -0.53
     passés
    -0.53
     căr
    -0.52
     viață
    -0.52
    POSITIVE LOGITS
    console
    0.88
     console
    0.87
     !==
    0.65
    const
    0.65
     window
    0.63
     const
    0.62
     ===
    0.62
    (()
    0.62
     flyknit
    0.59
    PreferredItem
    0.59
    Activations Density 0.086%

    No Known Activations