© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15304
    Prev
    Next
    INDEX
    Explanations

    references to plants and shrubs, particularly in a gardening or horticultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.09
     ExecuteAsync
    -0.76
    EndProject
    -0.74
     EconPapers
    -0.71
    setVerticalGroup
    -0.71
    Geplaatst
    -0.70
     protoimpl
    -0.69
     kasarigan
    -0.69
     saites
    -0.67
    GeneratedCode
    -0.66
    POSITIVE LOGITS
     dây
    0.56
     lambat
    0.50
     Bäume
    0.49
     piante
    0.48
    keyDown
    0.47
     chevaux
    0.47
     árvores
    0.47
    leaflet
    0.46
    juga
    0.46
    Boletín
    0.46
    Activations Density 0.237%

    No Known Activations