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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 475
    Prev
    Next
    INDEX
    Explanations

    references to individuals' professional backgrounds and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.68
    المشاركات
    -0.58
     فريبيس
    -0.56
    hoeddwyd
    -0.54
    Климат
    -0.53
     otomatig
    -0.50
    tanleria
    -0.48
    تقاوى
    -0.47
    Хьажоргаш
    -0.47
    хьтан
    -0.46
    POSITIVE LOGITS
    ViewImports
    0.50
    期刊论文
    0.47
     "..\..\
    0.40
    BorderFactory
    0.39
     BoxFit
    0.38
     Zufall
    0.38
     singkat
    0.38
     kejadian
    0.36
     Kooperation
    0.36
     Verkaufs
    0.36
    Activations Density 1.750%

    No Known Activations