© 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. 13050
    Prev
    Next
    INDEX
    Explanations

    expressions related to user interface layout in programming code

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

    Code, file names, and technical jargon

    np_acts-logits-general · gemini-2.0-flash

    android drawable and code snippets

    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
    
    -0.79
    interopRequire
    -0.64
    InSection
    -0.61
    Hozzáférés
    -0.59
    getItemId
    -0.58
    __*/
    -0.56
    ScopeManager
    -0.56
     AssemblyCulture
    -0.53
    PageContext
    -0.52
    AccessorTable
    -0.51
    POSITIVE LOGITS
    layout
    0.58
    Гео
    0.55
     layout
    0.54
    localctx
    0.54
    setContentView
    0.53
    balleur
    0.53
    __":
    0.52
    anskje
    0.52
    voorbeeld
    0.51
    ~~~~~~~~~~~~~~~~
    0.51
    Activations Density 0.046%

    No Known Activations