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. 5-GEMMASCOPE-RES-16K
    6. 10143
    Prev
    Next
    INDEX
    Explanations

    elements related to tabs and tabbed interfaces in a user interface or application context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?>
    
    -0.67
     Kongo
    -0.67
    machung
    -0.66
     Vinci
    -0.65
    "</
    -0.64
     ?>">
    -0.62
    resu
    -0.62
     Theodor
    -0.62
     operacional
    -0.61
    ésia
    -0.61
    POSITIVE LOGITS
     tab
    2.54
     Tab
    2.38
    Tab
    2.31
     tabs
    2.27
    tab
    2.21
     Tabs
    2.12
     TAB
    2.03
    TAB
    1.91
    tabs
    1.90
    Tabs
    1.68
    Activations Density 0.047%

    No Known Activations