© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12655
    Prev
    Next
    INDEX
    Explanations

    references to Danish individuals and their historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.81
     autorytatywna
    -0.79
     propOrder
    -0.74
     Efq
    -0.74
     nød
    -0.69
    iſter
    -0.65
     Houſe
    -0.63
    GEBURTSDATUM
    -0.63
     Normdatei
    -0.61
    DockStyle
    -0.60
    POSITIVE LOGITS
     Danish
    0.71
     Copenhagen
    0.64
    Danish
    0.62
     Denmark
    0.62
    Denmark
    0.57
     Dinamarca
    0.56
     dansk
    0.53
     Danmark
    0.52
     Dänemark
    0.48
     danish
    0.47
    Activations Density 0.483%

    No Known Activations