© 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. 3-GEMMASCOPE-RES-16K
    11. 1274
    Prev
    Next
    INDEX
    Explanations

    words associated with kindness and positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.88
    IsContent
    -0.87
    makeConstraints
    -0.77
     Drapeau
    -0.75
    DockStyle
    -0.71
    rrggbb
    -0.69
    GMENT
    -0.67
     egna
    -0.66
    AddTagHelper
    -0.65
    KommentareTeilen
    -0.64
    POSITIVE LOGITS
     kindness
    1.16
    kindness
    0.97
     Kindness
    0.96
     generosity
    0.90
     generous
    0.84
     kindly
    0.83
     charitable
    0.80
     unkind
    0.79
     compassionate
    0.76
     kinder
    0.71
    Activations Density 0.362%

    No Known Activations