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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92450
    Prev
    Next
    INDEX
    Explanations

    JavaScript syntax elements and structural patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RenderAtEndOf
    -1.04
     ujednoznacz
    -0.95
     للمعارف
    -0.90
    IUrlHelper
    -0.85
    tagHelperRunner
    -0.81
     Normdatei
    -0.81
     Мексичка
    -0.80
    rungsseite
    -0.79
    AnimationsModule
    -0.78
    IVEREF
    -0.77
    POSITIVE LOGITS
      
    0.43
     overnight
    0.37
     instantly
    0.36
     sekaligus
    0.34
     başlay
    0.33
    setState
    0.33
     suficientemente
    0.32
     faster
    0.32
     started
    0.32
    ↵↵
    0.31
    Activations Density 0.001%

    No Known Activations