© 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. 5-GEMMASCOPE-RES-16K
    11. 7108
    Prev
    Next
    INDEX
    Explanations

    phrases related to caregiving and concern for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vdash
    -0.82
     craindre
    -0.72
      
    -0.70
     soudain
    -0.69
    indépendance
    -0.68
    ುವ
    -0.67
     lourd
    -0.64
     Kies
    -0.63
     Thy
    -0.62
     aborto
    -0.62
    POSITIVE LOGITS
     AssemblyCulture
    0.84
     estekak
    0.80
     متعلقه
    0.76
     arşivlendi
    0.74
    miyor
    0.70
     CreateTagHelper
    0.66
    AnimationsModule
    0.65
     rid
    0.65
    UrlResolution
    0.63
    parsedMessage
    0.62
    Activations Density 0.093%

    No Known Activations