© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10209
    Prev
    Next
    INDEX
    Explanations

    references to German identity and associated cultural elements

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

    Germany or Germans

    np_acts-logits-general · gemini-2.0-flash

    Germans, Germany, German, Germanic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Wolken
    -0.75
     Nieren
    -0.73
     Teig
    -0.73
    kissen
    -0.70
     Futter
    -0.69
     Wład
    -0.69
     Kugel
    -0.68
     Klagen
    -0.68
     Zwiebel
    -0.68
     Ră
    -0.68
    POSITIVE LOGITS
     Tuchel
    0.51
     Bewußt
    0.47
     Verwendung
    0.47
     Einfluß
    0.46
    sello
    0.45
     Germany
    0.44
     alemão
    0.44
     deutschen
    0.44
     tedesco
    0.44
     Duitse
    0.43
    Activations Density 0.524%

    No Known Activations