© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 16033
    Prev
    Next
    INDEX
    Explanations

    terms that express respect and consideration for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externi
    -0.57
    UnusedPrivate
    -0.57
     насељу
    -0.56
     continúas
    -0.53
    apimachinery
    -0.53
     ujednoznacz
    -0.51
     SEDS
    -0.51
    diag
    -0.49
     continuant
    -0.49
    Saharan
    -0.49
    POSITIVE LOGITS
     respect
    2.14
     Respect
    2.10
    Respect
    2.03
     respectful
    2.01
    respect
    1.99
     respecting
    1.86
     RESPECT
    1.80
     respects
    1.68
     respeto
    1.61
     respekt
    1.55
    Activations Density 0.303%

    No Known Activations