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. 15983
    Prev
    Next
    INDEX
    Explanations

    code elements and programming structures, particularly those related to function definitions and mathematical calculations

    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
    :✨
    -0.72
     autorytatywna
    -0.70
    IndentedString
    -0.61
     NSCoder
    -0.60
    protoimpl
    -0.60
    __":
    
    -0.57
    Handlung
    -0.54
    ValueGenerated
    -0.54
     CURIAM
    -0.54
    __':
    
    -0.53
    POSITIVE LOGITS
     divided
    1.71
     /
    1.52
     divide
    1.52
     dividing
    1.40
    /(
    1.38
    divide
    1.37
    divided
    1.32
     divides
    1.31
     Divided
    1.29
     dividido
    1.28
    Activations Density 2.200%

    No Known Activations