© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7188
    Prev
    Next
    INDEX
    Explanations

    references to Dutch people, culture, or entities

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

    Dutch language or Netherlands

    np_acts-logits-general · gemini-2.0-flash

    Netherlands and Dutch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     handen
    -0.56
     voeten
    -0.46
     Sonn
    -0.43
    kijken
    -0.42
     escuchado
    -0.41
     cumplido
    -0.41
     gehad
    -0.40
     asesinado
    -0.38
    leiter
    -0.37
     guerr
    -0.36
    POSITIVE LOGITS
     Dutch
    1.31
    Dutch
    1.17
     dutch
    1.16
     Netherlands
    1.16
     Dutchman
    1.15
    荷兰
    1.13
    Netherlands
    1.11
     holand
    1.09
    Holland
    1.08
     Holland
    1.05
    Activations Density 0.166%

    No Known Activations