© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6850
    Prev
    Next
    INDEX
    Explanations

    references to the European Union and European entities

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

    references to Europe or the European Union.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    baiki
    -0.43
     Batalla
    -0.41
     presidencial
    -0.39
    ambilan
    -0.37
     Nacionales
    -0.36
     incendios
    -0.34
     Brasilien
    -0.34
     cancha
    -0.32
     Stimme
    -0.31
     Gerechtigkeit
    -0.31
    POSITIVE LOGITS
     Eura
    1.04
    Europe
    1.03
     Europe
    1.02
     EURO
    1.02
     Europ
    1.01
     EUROPE
    0.98
     europe
    0.98
     europ
    0.97
    europe
    0.97
     EU
    0.97
    Activations Density 0.038%

    No Known Activations