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

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 11327
    Prev
    Next
    INDEX
    Explanations

    references to commonly used terms or phrases that indicate continuation or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    事情
    -0.51
    рь
    -0.49
    いただきたい
    -0.48
    ILabel
    -0.48
    ת
    -0.47
    ValueStyle
    -0.46
    vite
    -0.46
     alternativ
    -0.46
    뢰
    -0.45
    תה
    -0.45
    POSITIVE LOGITS
     etc
    3.05
    etc
    2.87
     Etc
    2.50
    Etc
    2.37
     usw
    2.11
     ETC
    1.87
     등
    1.74
     ect
    1.70
    等
    1.67
    ETC
    1.66
    Activations Density 0.099%

    No Known Activations