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. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4731
    Prev
    Next
    INDEX
    Explanations

    references to Windows and related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    CompleteListener
    -0.52
     ویکی‌پدیا
    -0.51
    complexType
    -0.51
    ViewFeatures
    -0.51
     ''}
    -0.48
    granate
    -0.48
    cokinetic
    -0.48
    Checksum
    -0.48
    ed
    -0.47
     EconPapers
    -0.47
    POSITIVE LOGITS
    Windows
    0.77
     فريبيس
    0.71
     חיצוניים
    0.67
     Wales
    0.64
     Windows
    0.64
    hhhhhhhh
    0.62
     iconTwitter
    0.62
     Sist
    0.61
     Obispo
    0.59
     WIN
    0.58
    Activations Density 0.021%

    No Known Activations