© 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. 935
    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
    TemporalType
    -0.72
    strophic
    -0.69
     Dene
    -0.67
    ]:
    
    -0.65
     Duy
    -0.65
    šanai
    -0.64
     Loaf
    -0.63
    ēju
    -0.63
     Vinh
    -0.63
     Hyun
    -0.60
    POSITIVE LOGITS
    arakhand
    0.66
     समीक्षक
    0.62
     India
    0.60
    GEBURTSDATUM
    0.60
    LogFactory
    0.57
    RegressionTest
    0.56
    PostExecute
    0.56
     saksi
    0.56
    anskrit
    0.55
    انتهای
    0.54
    Activations Density 0.071%

    No Known Activations