Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 58998
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical user interface (GUI) dimensions and layout components

    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
    htiö
    -0.36
    stdc
    -0.35
    发表于
    -0.34
     intStringLen
    -0.31
    Спољашње
    -0.31
    pytest
    -0.31
    ellschaft
    -0.28
    ۜ
    -0.28
     ")");
    -0.28
    //*/
    -0.28
    POSITIVE LOGITS
    awtextra
    0.74
     autorytatywna
    0.71
    tableFuture
    0.69
    IBarButtonItem
    0.65
    WaitGroup
    0.63
    ComponentName
    0.62
    SocketAddress
    0.61
     AssemblyTitle
    0.59
    Dimension
    0.56
    AttributedString
    0.56
    Activations Density 0.003%

    No Known Activations