© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5911
    Prev
    Next
    INDEX
    Explanations

    instances of content related to events or announcements, particularly formal ones

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

    Non-ASCII characters

    np_acts-logits-general · gemini-2.0-flash

    word followed by specific word

    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
    Personensuche
    -0.78
    TagMode
    -0.73
    ihnachten
    -0.65
    ency
    -0.63
     StatelessWidget
    -0.62
    WriteLiteral
    -0.62
    AccessorTable
    -0.62
    
    -0.62
     Мексичка
    -0.60
     eventdata
    -0.60
    POSITIVE LOGITS
    }^{-}
    0.62
     
    0.62
     Penh
    0.60
     Portail
    0.57
    ❤️❤️
    0.57
    processData
    0.55
     sauter
    0.54
     Paglinawan
    0.53
    retz
    0.52
     mesurer
    0.52
    Activations Density 0.265%

    No Known Activations