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-2-2B
    4. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8803
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Massara," indicating a focus on a specific individual or entity in the context of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ara
    -2.48
    ARA
    -2.03
    aras
    -1.20
    araan
    -1.04
    Ara
    -0.90
     ara
    -0.88
    ară
    -0.88
    aran
    -0.88
    arah
    -0.86
    arao
    -0.86
    POSITIVE LOGITS
     ویکی‌پدی
    0.77
     kasarigan
    0.68
     وتسجيلات
    0.66
    хьтан
    0.62
     חיצוניים
    0.61
    Tikang
    0.60
     thiệu
    0.60
     שוליים
    0.60
    /******/
    0.59
    تفصیلات
    0.59
    Activations Density 0.187%

    No Known Activations