© 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. 16-GEMMASCOPE-RES-16K
    11. 7040
    Prev
    Next
    INDEX
    Explanations

    fragments of mathematical notation and variables

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

    LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setof
    -0.56
    adpleegd
    -0.55
    <eos>
    -0.53
    ↵↵
    -0.52
    諏訪
    -0.50
    ↵↵↵
    -0.50
     Stück
    -0.49
    [[
    -0.47
    ent
    -0.47
     ente
    -0.46
    POSITIVE LOGITS
     GenerationType
    1.08
    djangoproject
    1.04
     للمعارف
    1.02
    BeginContext
    0.98
    </>
    0.98
    interopRequire
    0.98
    tvguidetime
    0.96
    !*\
    0.96
     فريبيس
    0.94
     isComment
    0.94
    Activations Density 0.022%

    No Known Activations