© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7922
    Prev
    Next
    INDEX
    Explanations

    events and contracts related to sports teams and player signings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.69
    AddTagHelper
    -0.66
     maupun
    -0.62
     dacă
    -0.59
     powinny
    -0.59
     daca
    -0.58
     zwłaszcza
    -0.58
     szczególnie
    -0.57
     nếu
    -0.57
     если
    -0.57
    POSITIVE LOGITS
     shortly
    0.95
     followed
    0.95
     becoming
    0.94
     whereupon
    0.93
    becoming
    0.86
     after
    0.85
    followed
    0.84
     Shortly
    0.78
     following
    0.77
     nachdem
    0.75
    Activations Density 1.388%

    No Known Activations