© 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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 655
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    醐
    -0.66
    (!__
    -0.65
     مشارکت‌کنندگان
    -0.65
    termilk
    -0.64
    MemoryWarning
    -0.64
     AspNetCore
    -0.63
    onets
    -0.63
     Wikimedijinoj
    -0.62
    exitRule
    -0.61
     '\\;'
    -0.61
    POSITIVE LOGITS
     jewelry
    1.33
     jewellery
    1.21
     Jewelry
    1.04
    jewelry
    1.01
    Jewelry
    1.00
     jewel
    1.00
     jew
    0.97
     Jewellery
    0.94
     jewels
    0.92
    jew
    0.91
    Activations Density 0.026%

    No Known Activations