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. 13571
    Prev
    Next
    INDEX
    Explanations

    sections or elements related to statistical notation and algebra

    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
     ویکی‌پدی
    -0.99
    которые
    -0.96
    bootstrapcdn
    -0.94
    withstanding
    -0.94
    viembre
    -0.89
     ―――――
    -0.83
     autorytatywna
    -0.82
    NUMX
    -0.82
     Efq
    -0.81
    ^(@)
    -0.79
    POSITIVE LOGITS
    Слайд
    0.63
    CADE
    0.62
    页面存档备份
    0.61
    ksanakan
    0.59
     مرئيه
    0.58
    selaer
    0.53
     /
    0.53
     出版
    0.53
      
    0.51
     $^{\
    0.51
    Activations Density 1.295%

    No Known Activations