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. 5-GEMMASCOPE-RES-16K
    6. 8739
    Prev
    Next
    INDEX
    Explanations

    phrases relating to main points, issues, and objectives in various contexts

    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
     InputDecoration
    -0.62
    thető
    -0.53
     tombé
    -0.52
    こちらも
    -0.51
    tigas
    -0.50
     Biôgrafia
    -0.50
     benzer
    -0.49
     NDEBUG
    -0.48
    Dare
    -0.47
     иначе
    -0.47
    POSITIVE LOGITS
     main
    1.84
     principale
    1.71
     principaux
    1.57
     principal
    1.55
     MAIN
    1.52
     utama
    1.49
     głów
    1.48
     principales
    1.47
    main
    1.46
     Main
    1.44
    Activations Density 0.260%

    No Known Activations