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. 12606
    Prev
    Next
    INDEX
    Explanations

    elements and classes related to user interface components and settings in coding languages, specifically for Android and Java

    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
    contentLoaded
    -0.78
     saurait
    -0.75
     lumineuse
    -0.73
     elettrico
    -0.72
    tableFuture
    -0.71
    ysław
    -0.70
     automatiques
    -0.69
    +:+
    -0.69
     extérieure
    -0.68
     touristes
    -0.67
    POSITIVE LOGITS
    (!__
    0.65
    urto
    0.52
    appcompat
    0.51
     fleet
    0.51
     odd
    0.51
     androidx
    0.50
     fl
    0.50
    スタート
    0.49
     Mayo
    0.49
    avits
    0.49
    Activations Density 0.015%

    No Known Activations