© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14894
    Prev
    Next
    INDEX
    Explanations

    patterns and structures commonly used in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withOpacity
    -0.59
    TagMode
    -0.58
    IsMutable
    -0.55
    новниш
    -0.55
     Infórmanos
    -0.52
    MessageOf
    -0.52
    Bedrooms
    -0.51
    Vidite
    -0.51
     ✭✭
    -0.50
    fromnode
    -0.50
    POSITIVE LOGITS
    UnusedPrivate
    0.57
     considérons
    0.44
    addComponent
    0.40
     mergeFrom
    0.37
    multicolumn
    0.34
     quiero
    0.32
    
    0.32
    fetchone
    0.32
    Hauptartikel
    0.31
    colhead
    0.30
    Activations Density 0.376%

    No Known Activations