© 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. 30-GEMMASCOPE-RES-16K
    11. 10897
    Prev
    Next
    INDEX
    Explanations

    names of places, people, and organizations, particularly those related to Denmark

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

    Denmark or Danish topics

    np_acts-logits-general · gemini-2.0-flash

    Danish and Denmark

    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
     nød
    -0.88
     queſta
    -0.81
     disambiguazione
    -0.77
    føring
    -0.74
     ſind
    -0.74
     beſte
    -0.73
    hæng
    -0.72
    ſelf
    -0.71
     Houſe
    -0.71
     stockbild
    -0.70
    POSITIVE LOGITS
     Danish
    0.95
     Copenhagen
    0.82
    Danish
    0.80
     Denmark
    0.77
     danish
    0.71
    Denmark
    0.69
     Jensen
    0.63
     Dinamarca
    0.60
     Sø
    0.60
     Rasmussen
    0.58
    Activations Density 0.525%

    No Known Activations