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. 3-GEMMASCOPE-RES-16K
    6. 12079
    Prev
    Next
    INDEX
    Explanations

    references to international organizations or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     énergé
    -0.75
    LogFactory
    -0.75
    écou
    -0.73
     présidenti
    -0.73
     vertes
    -0.71
     للاسماء
    -0.71
     épis
    -0.69
     élector
    -0.69
     dueño
    -0.67
     chré
    -0.66
    POSITIVE LOGITS
     international
    2.96
     International
    2.88
    International
    2.79
    international
    2.71
     INTERNATIONAL
    2.50
     internationale
    2.40
    INTERNATIONAL
    2.39
     Internation
    2.32
     internation
    2.32
     internacional
    2.25
    Activations Density 0.054%

    No Known Activations