© 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. 1578
    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
    twimg
    -0.70
    SBATCH
    -0.69
     ProtoMessage
    -0.68
    readFileSync
    -0.64
    modelBuilder
    -0.61
    complexContent
    -0.60
    aarrggbb
    -0.58
    expandindo
    -0.58
     terminated
    -0.58
    ⓧ
    -0.57
    POSITIVE LOGITS
     tips
    1.38
     advice
    1.26
     Tips
    1.17
    Tips
    1.16
     suggestions
    1.10
     TIPS
    1.06
    tips
    1.04
     recommendations
    1.02
     hints
    1.02
     Advice
    1.00
    Activations Density 0.039%

    No Known Activations