© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9819
    Prev
    Next
    INDEX
    Explanations

    references to specific ethnic groups, particularly Germans and related demographics in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Teig
    -0.77
     Futter
    -0.75
     Nieren
    -0.75
     Wolken
    -0.72
     Glä
    -0.71
     Kugel
    -0.71
     Seil
    -0.71
     InputDecoration
    -0.71
     Baus
    -0.70
     Wład
    -0.69
    POSITIVE LOGITS
     Einfluß
    0.51
     Bewußt
    0.50
     Tuchel
    0.48
     tedesco
    0.48
     alemão
    0.47
     Verwendung
    0.44
     alemana
    0.43
     industriels
    0.43
     Vettel
    0.42
     kış
    0.42
    Activations Density 0.382%

    No Known Activations