© 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. 9-GEMMASCOPE-RES-16K
    11. 16028
    Prev
    Next
    INDEX
    Explanations

    phrases questioning or explaining reasons and motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknownFields
    -0.78
    CodedInputStream
    -0.62
    IUrlHelper
    -0.59
     CreateTagHelper
    -0.56
    ญิง
    -0.55
    ädie
    -0.54
    DeleteBehavior
    -0.53
     zewnętrzne
    -0.51
     circonst
    -0.51
     Pring
    -0.49
    POSITIVE LOGITS
     why
    0.85
     Daarom
    0.76
     Derfor
    0.75
     فريبيس
    0.74
     weshalb
    0.72
     Dlatego
    0.72
     للمعارف
    0.71
     dlatego
    0.69
    HasForeignKey
    0.66
    ViewFeatures
    0.66
    Activations Density 0.255%

    No Known Activations