© 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. 20-GEMMASCOPE-RES-16K
    11. 471
    Prev
    Next
    INDEX
    Explanations

    references to kindness and forgiveness in the context of interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Kindness, forgiveness, and compassion

    np_acts-logits-general · gemini-2.0-flash

    kindness and leniency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.66
    makeConstraints
    -0.61
     proudly
    -0.54
    eseed
    -0.50
     spørgsmål
    -0.49
    фек
    -0.49
    INSEE
    -0.48
    WithIOException
    -0.48
    cassert
    -0.47
    aarrggbb
    -0.47
    POSITIVE LOGITS
     mercy
    1.61
     lenient
    1.49
     forgiving
    1.48
     compassion
    1.47
     merciful
    1.47
     kindness
    1.39
     compassionate
    1.35
     sympathetic
    1.29
     clemen
    1.29
     sympathy
    1.28
    Activations Density 0.440%

    No Known Activations