© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11413
    Prev
    Next
    INDEX
    Explanations

    references to political events and entities in Germany

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

    Germany or German-related topics

    np_acts-logits-general · gemini-2.0-flash

    Germany and German historical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brust
    -0.97
     Nieren
    -0.96
     Mühle
    -0.92
     Katze
    -0.91
     Bienen
    -0.91
     Stirn
    -0.90
     Wolken
    -0.90
     Orgel
    -0.87
     Kleid
    -0.86
     Erde
    -0.85
    POSITIVE LOGITS
     Germany
    0.73
     German
    0.70
    ドイツ
    0.63
    Germany
    0.61
     germany
    0.59
     آلمان
    0.57
    German
    0.57
     Duitse
    0.56
    德国
    0.54
     Германии
    0.52
    Activations Density 1.181%

    No Known Activations