Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 47506
    Prev
    Next
    INDEX
    Explanations

    references to Norway and related cultural or scientific entities

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

    Norway and Norwegian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.60
    ptonshire
    -0.57
    postIndex
    -0.56
     arbejds
    -0.54
     disambiguazione
    -0.53
    BagLayout
    -0.53
    hæng
    -0.52
     Jiangsu
    -0.51
    icago
    -0.50
    styleType
    -0.50
    POSITIVE LOGITS
     Norway
    1.00
     Norwegian
    0.94
    Norway
    0.91
     Noruega
    0.90
    Norwegian
    0.88
    Oslo
    0.78
     Norvège
    0.76
     Norwe
    0.74
     Oslo
    0.73
     fjord
    0.68
    Activations Density 0.036%

    No Known Activations