© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1799
    Prev
    Next
    INDEX
    Explanations

    references to Dutch culture and history, particularly related to Jewish individuals and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voeten
    -0.53
     handen
    -0.49
    genodigd
    -0.47
     dezelve
    -0.47
     zelve
    -0.46
     zoude
    -0.46
     escuchado
    -0.45
     geschenk
    -0.43
     genomen
    -0.42
     ayudado
    -0.42
    POSITIVE LOGITS
     Dutch
    1.58
     dutch
    1.39
    Dutch
    1.39
     Netherlands
    1.33
    荷兰
    1.31
     Dutchman
    1.29
     Holland
    1.25
    Netherlands
    1.22
     holand
    1.22
    dutch
    1.20
    Activations Density 0.239%

    No Known Activations