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. 3935
    Prev
    Next
    INDEX
    Explanations

    references to practical applications of concepts or studies in real-world scenarios

    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
    PerformLayout
    -0.59
    ViewImports
    -0.59
     BoxDecoration
    -0.57
    canakan
    -0.54
    最快更新
    -0.48
    válasz
    -0.48
    +#+#
    -0.48
     Adkins
    -0.47
    GeneratedValue
    -0.46
    šel
    -0.46
    POSITIVE LOGITS
     reality
    0.98
     practical
    0.98
     prakty
    0.96
     praktijk
    0.96
    Практи
    0.94
     realities
    0.93
    實際
    0.92
     irl
    0.90
    实际
    0.90
     PRACTICAL
    0.90
    Activations Density 0.357%

    No Known Activations