© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 76755
    Prev
    Next
    INDEX
    Explanations

    references to Nordic or Scandinavian entities or concepts

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

    Nordic and Scandinavian countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toilette
    -0.44
     Wiss
    -0.43
    unsqueeze
    -0.42
     soja
    -0.41
     oportun
    -0.39
    Shame
    -0.39
     zom
    -0.39
     Gez
    -0.39
    τζ
    -0.38
     Immort
    -0.38
    POSITIVE LOGITS
     Nordic
    2.14
    Nordic
    1.99
     nordic
    1.67
     Scandinavian
    1.54
    nordic
    1.53
     Scandinavia
    1.39
     nór
    1.26
    北欧
    1.16
    andinavian
    1.13
    andinav
    1.08
    Activations Density 0.005%

    No Known Activations