© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5358
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.83
     dreamstime
    -0.81
     Havel
    -0.74
     nahilalakip
    -0.74
     Shrine
    -0.73
     Anſ
    -0.73
     PRS
    -0.71
    setVerticalGroup
    -0.71
    Gambas
    -0.71
     Kanna
    -0.70
    POSITIVE LOGITS
     Ed
    3.18
    Ed
    2.93
     ed
    2.87
     ED
    2.44
    ED
    2.04
    ed
    1.98
     Eds
    1.92
     eds
    1.84
    Eds
    1.59
     Edmond
    1.50
    Activations Density 0.117%

    No Known Activations