© 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. 20-GEMMASCOPE-RES-16K
    11. 12312
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that represent dialogue or quotations

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

    Roman empire/history context

    np_acts-logits-general · gemini-2.0-flash

    Roman calendar, festivals

    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
    PerformLayout
    -0.72
     الحره
    -0.63
    Skocz
    -0.59
    pidou
    -0.55
    BeginInit
    -0.54
    ⓘ
    -0.53
     المعيارى
    -0.53
    AccessorTable
    -0.51
     ujednoznacz
    -0.51
    出版年
    -0.49
    POSITIVE LOGITS
     Roman
    0.99
    Roman
    0.89
     Rome
    0.82
     ROMAN
    0.81
     Romans
    0.80
     roman
    0.80
     Caesar
    0.79
     romana
    0.77
    Caesar
    0.74
     Caesars
    0.74
    Activations Density 0.161%

    No Known Activations