© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8806
    Prev
    Next
    INDEX
    Explanations

    references to Dutch culture, people, or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    genodigd
    -0.62
     betrek
    -0.59
     voeten
    -0.59
     gekomen
    -0.55
     zoude
    -0.55
     geïsole
    -0.52
     goederen
    -0.52
    évaluateur
    -0.51
     moeite
    -0.50
     vermogen
    -0.50
    POSITIVE LOGITS
     Dutch
    0.95
     dutch
    0.92
    Dutch
    0.86
    dutch
    0.82
    Voor
    0.70
    Mijn
    0.68
     Rotterdam
    0.68
     Hoog
    0.67
     Dutchman
    0.66
     VOOR
    0.66
    Activations Density 1.081%

    No Known Activations