© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 70
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

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

    programming-related syntax and function definitions

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

    programming concepts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    addTo
    -0.51
     racconto
    -0.46
     amounts
    -0.45
     speciale
    -0.45
     înd
    -0.45
     emlé
    -0.44
     lø
    -0.44
    emploi
    -0.43
     istimewa
    -0.42
     pregă
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.86
    AccessorTable
    0.86
    IBOutlet
    0.80
    DockStyle
    0.74
    ReusableCell
    0.72
    sizeCache
    0.71
     disambiguazione
    0.71
    BeginContext
    0.68
    thâu
    0.68
    verwijspagina
    0.67
    Activations Density 0.023%

    No Known Activations