© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7404
    Prev
    Next
    INDEX
    Explanations

    technical terms related to storage and data structures

    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
     yoghurt
    -0.84
     aeroplane
    -0.84
     Ramadhan
    -0.82
     Palae
    -0.79
     Whatsapp
    -0.77
     Beverley
    -0.76
     Enquiry
    -0.75
     Encyclopaedia
    -0.75
     sulphur
    -0.75
     ageing
    -0.75
    POSITIVE LOGITS
     Larson
    0.77
     gage
    0.70
     Czar
    0.69
     Frazier
    0.67
     Shepard
    0.66
    Stacy
    0.64
     Stacy
    0.62
     Murdock
    0.61
     gages
    0.61
     McCullough
    0.59
    Activations Density 2.902%

    No Known Activations