© 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. 20-GEMMASCOPE-RES-16K
    11. 8628
    Prev
    Next
    INDEX
    Explanations

    references to notes or citations within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    note that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -1.22
     betweenstory
    -1.03
    RegressionTest
    -0.98
    InjectAttribute
    -0.97
     JpaRepository
    -0.93
     kasarigan
    -0.92
     itſelf
    -0.92
     Jefus
    -0.91
     فريبيس
    -0.91
    ftagPool
    -0.90
    POSITIVE LOGITS
     also
    1.01
     again
    0.88
     additionally
    0.75
     inoltre
    0.71
     moreover
    0.69
     finally
    0.67
     además
    0.67
     furthermore
    0.65
     infine
    0.65
     toutefois
    0.63
    Activations Density 0.507%

    No Known Activations