© 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. 1362
    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
     surla
    -0.66
    MessageTagHelper
    -0.66
    ContextHolder
    -0.61
    tizia
    -0.57
     "','
    -0.56
    kadot
    -0.56
     poveznice
    -0.55
    UrlResolution
    -0.54
    WithIOException
    -0.54
    korn
    -0.53
    POSITIVE LOGITS
     difficult
    1.05
    difficult
    0.94
     arduous
    0.93
     daunting
    0.90
     challenging
    0.88
     Difficult
    0.87
     tricky
    0.84
     complicated
    0.84
    Difficult
    0.79
     toughest
    0.78
    Activations Density 0.135%

    No Known Activations