© 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. 6-GEMMASCOPE-RES-16K
    6. 12829
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "design."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -1.05
    AllAfrica
    -0.87
     pitié
    -0.86
     Geophysics
    -0.82
    fycat
    -0.81
     snippetHide
    -0.78
     Holbrook
    -0.77
     ویکی‌پدیای
    -0.76
     hearsay
    -0.76
    Sympto
    -0.76
    POSITIVE LOGITS
     design
    2.15
     designs
    1.94
     Design
    1.92
    Design
    1.89
    design
    1.76
     Designs
    1.63
    designs
    1.63
    DESIGN
    1.62
     DESIGN
    1.61
     designers
    1.56
    Activations Density 0.060%

    No Known Activations