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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16059
    Prev
    Next
    INDEX
    Explanations

    key terms related to economic and regulatory concepts in the European Union

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

    European entities or medicines agencies

    np_acts-logits-general · gemini-2.0-flash

    European Parliament and EU Commission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaan
    -0.46
    WebVitals
    -0.45
     ExecuteAsync
    -0.44
    ölkerung
    -0.43
     Whittier
    -0.41
     canad
    -0.40
     Zion
    -0.40
    intios
    -0.40
    참고
    -0.40
     iNdEx
    -0.39
    POSITIVE LOGITS
     European
    1.09
     EU
    1.08
    European
    1.03
     EUROPEAN
    0.95
    EU
    0.93
     euro
    0.88
     Europese
    0.87
     europäischen
    0.86
     Europeans
    0.85
    欧洲
    0.84
    Activations Density 0.137%

    No Known Activations