© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9335
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "do" in various forms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     wort
    -0.53
    下载附件
    -0.48
     acorns
    -0.48
     Bish
    -0.48
     Corning
    -0.47
     ź
    -0.47
    expandindo
    -0.46
     BNE
    -0.46
    rible
    -0.46
     Majors
    -0.45
    POSITIVE LOGITS
     del
    1.21
    OfThe
    1.09
    ofthe
    1.09
     ofthe
    1.01
     du
    0.99
     dello
    0.95
     dels
    0.95
     του
    0.91
     dei
    0.88
     delle
    0.88
    Activations Density 0.041%

    No Known Activations