© 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 - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1274
    Prev
    Next
    INDEX
    Explanations

    terms related to cleaning or clearing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.59
     épar
    -0.51
    tvguidetime
    -0.49
     Addams
    -0.48
     commerciaux
    -0.46
    WireFormatLite
    -0.46
    AutoSize
    -0.46
    Це
    -0.46
     FetchType
    -0.46
    WebServlet
    -0.46
    POSITIVE LOGITS
     blown
    0.81
     blow
    0.80
     blew
    0.77
     blowout
    0.75
     Blow
    0.73
    glClear
    0.72
    blow
    0.71
    blown
    0.71
     clearing
    0.67
    ViewFeatures
    0.66
    Activations Density 0.486%

    No Known Activations