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. 2801
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and biological processes

    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
     Twain
    -0.98
     mdi
    -0.90
     Carla
    -0.82
    Carla
    -0.81
     Mehdi
    -0.76
     Frazer
    -0.76
     Madi
    -0.76
    QtWidgets
    -0.75
     SDI
    -0.74
    terase
    -0.73
    POSITIVE LOGITS
    pyx
    0.87
    ghton
    0.79
     Kirs
    0.78
     تضيفلها
    0.77
    Guido
    0.76
     Guido
    0.75
     Sway
    0.74
     Mors
    0.74
    Babylon
    0.73
     Reverso
    0.73
    Activations Density 2.542%

    No Known Activations