© 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. 1-GEMMASCOPE-RES-16K
    11. 7632
    Prev
    Next
    INDEX
    Explanations

    references to physical proximity or closeness in relationships or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
    queryInterface
    -0.66
    IsMutable
    -0.63
     humains
    -0.63
     发表于
    -0.59
    PageRoute
    -0.58
    QMetaType
    -0.56
    getLogger
    -0.56
     AssemblyCompany
    -0.55
    wherein
    -0.55
    POSITIVE LOGITS
     close
    5.11
     Close
    4.31
    close
    4.27
    Close
    4.07
     CLOSE
    4.04
    CLOSE
    3.41
     closer
    3.00
     closest
    2.68
    closer
    2.63
     Closer
    2.57
    Activations Density 0.062%

    No Known Activations