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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 5252
    Prev
    Next
    INDEX
    Explanations

    phrases indicating primary subjects or main ideas in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.55
     InputDecoration
    -0.54
     BorderRadius
    -0.53
     Lightboxes
    -0.51
     refusé
    -0.51
    اهرة
    -0.50
     tôt
    -0.50
    titleMargin
    -0.49
     früh
    -0.48
    GOTREF
    -0.48
    POSITIVE LOGITS
     main
    1.05
     MAIN
    1.01
     Main
    1.00
    Main
    0.96
     principale
    0.93
    MAIN
    0.91
     principal
    0.88
    getMain
    0.87
    main
    0.86
     Haupt
    0.85
    Activations Density 0.270%

    No Known Activations