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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14858
    Prev
    Next
    INDEX
    Explanations

    common phrases or words in multiple languages, indicating multilingual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    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
     الإسلامية
    -0.93
     الفلسطينية
    -0.79
     الأخيرة
    -0.79
     السياسية
    -0.76
     الداخلية
    -0.76
     المالية
    -0.74
     propOrder
    -0.73
     الدولية
    -0.72
     الشخصية
    -0.71
     الجديدة
    -0.71
    POSITIVE LOGITS
     ال
    1.58
     המ
    1.55
     الم
    1.51
     الأ
    1.48
    الم
    1.39
     הה
    1.37
     الت
    1.34
     الس
    1.26
    الأ
    1.26
     وال
    1.25
    Activations Density 0.012%

    No Known Activations