© 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. 3-GEMMASCOPE-RES-16K
    6. 9442
    Prev
    Next
    INDEX
    Explanations

    method calls related to event subscriptions and toast messages

    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
    帖最后由
    -0.66
    OTS
    -0.56
    Tembelea
    -0.54
     Mosca
    -0.54
    
    -0.54
    واده
    -0.52
     impregn
    -0.52
     Havel
    -0.52
     Lumière
    -0.51
     архивлан
    -0.51
    POSITIVE LOGITS
    makeText
    1.08
    migrationBuilder
    0.96
    ]='\
    0.79
    ArrowToggle
    0.77
     invokingState
    0.73
     display
    0.71
    jsonwebtoken
    0.66
    DotNetBar
    0.65
    فحة
    0.63
    indexPath
    0.62
    Activations Density 0.135%

    No Known Activations