© 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. 22-GEMMASCOPE-RES-16K
    11. 7113
    Prev
    Next
    INDEX
    Explanations

    references to historical political contexts and figures

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

    Hungary or Hungarian

    np_acts-logits-general · gemini-2.0-flash

    new church

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     különböz
    -0.71
    AsUp
    -0.67
    Vanjske
    -0.66
    IndentedString
    -0.66
     Flamengo
    -0.65
     felb
    -0.63
     MenuView
    -0.63
    Geplaatst
    -0.62
     eszköz
    -0.61
     rése
    -0.61
    POSITIVE LOGITS
     Hungary
    1.35
     Hungarian
    1.34
     Budapest
    1.24
    Hungary
    1.22
    Hungarian
    1.19
    Budapest
    1.04
     Hongrie
    1.03
     Hung
    0.98
     Magyar
    0.94
     Ungarn
    0.93
    Activations Density 0.065%

    No Known Activations