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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2906
    Prev
    Next
    INDEX
    Explanations

    references to coding concepts and programming structures

    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
    addCriterion
    -0.61
     ricor
    -0.50
     cheveux
    -0.46
     molding
    -0.42
     planches
    -0.41
     кампа
    -0.40
    magna
    -0.40
     ressort
    -0.40
     película
    -0.40
     levier
    -0.40
    POSITIVE LOGITS
     communication
    0.96
     وتسجيلات
    0.80
     Communication
    0.79
    communication
    0.78
     COMMUNICATION
    0.77
     متعلقه
    0.76
     communicating
    0.76
     initComponents
    0.75
    المناصب
    0.74
     exchange
    0.74
    Activations Density 0.719%

    No Known Activations