Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3757
    Prev
    Next
    INDEX
    Explanations

    concepts related to kindness and generosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppo
    -0.52
    ője
    -0.51
    ekš
    -0.50
    AMENTO
    -0.49
    endphp
    -0.49
    thâu
    -0.49
    ragalactic
    -0.49
     createState
    -0.48
    ulsión
    -0.48
     ansi
    -0.47
    POSITIVE LOGITS
     kindness
    1.26
     compassionate
    1.16
     altru
    1.14
     compassion
    1.11
    kindness
    1.09
     Kindness
    1.09
     selfless
    1.01
     generosity
    0.98
    Compassion
    0.96
     unselfish
    0.96
    Activations Density 0.355%

    No Known Activations