© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5067
    Prev
    Next
    INDEX
    Explanations

    connections and interactions among different elements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ground
    -0.57
    mények
    -0.54
     adhesives
    -0.54
     adhesive
    -0.52
    ground
    -0.51
    ิ้น
    -0.51
    Sticker
    -0.50
     Putih
    -0.49
     末
    -0.48
    wallpapers
    -0.48
    POSITIVE LOGITS
     alternating
    0.94
     interwoven
    0.93
     intersper
    0.93
     interspersed
    0.91
     overlapping
    0.88
    Portail
    0.88
     juxta
    0.86
     alternation
    0.86
     intertw
    0.83
     complementary
    0.82
    Activations Density 0.432%

    No Known Activations