© 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. 666
    Prev
    Next
    INDEX
    Explanations

    distinctive numeric values or data points related to inventions and their timelines

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

    numerical references, particularly years and related data

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

    historical invented years

    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
    ÍC
    -0.54
    nsf
    -0.51
     culturelles
    -0.48
    كتوبر
    -0.48
     ό
    -0.46
     تعدى
    -0.46
    eneuve
    -0.45
    věř
    -0.45
     tromper
    -0.44
    自
    -0.44
    POSITIVE LOGITS
     disponibilités
    0.84
     autorytatywna
    0.77
     <>",
    0.71
    SharedCtor
    0.68
     itſelf
    0.65
    mannian
    0.64
     Meiji
    0.64
     noqa
    0.62
    unyai
    0.62
    MFC
    0.61
    Activations Density 0.040%

    No Known Activations