© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 667
    Prev
    Next
    INDEX
    Explanations

    comments and documentation sections in the code

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

    comments or documentation in code

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

    biological apoptosis and object 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
    ar
    -0.61
    y
    -0.61
    i
    -0.58
    uma
    -0.56
    いった
    -0.56
     conto
    -0.53
    defineProperty
    -0.52
     Richt
    -0.51
    ↵
    -0.51
     fiche
    -0.50
    POSITIVE LOGITS
    ArrowToggle
    0.79
    NUMX
    0.70
    URLException
    0.66
    dersfield
    0.66
    tvguidetime
    0.64
     nyelv
    0.63
    يميديا
    0.63
     gomma
    0.62
    وردار
    0.62
     odkazy
    0.62
    Activations Density 0.003%

    No Known Activations