© 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. 22-GEMMASCOPE-RES-16K
    11. 14245
    Prev
    Next
    INDEX
    Explanations

    the Japanese character "お" and its variations, indicating a focus on expressions of politeness or endearment

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

    Japanese utterances starting with "o" (お)

    np_acts-logits-general · gemini-2.0-flash

    japanese honorific prefix お

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bäst
    -0.61
    kuat
    -0.60
     kaynağından
    -0.58
     icône
    -0.56
     fahrrad
    -0.56
    formaz
    -0.55
    ❋
    -0.55
    \}\\
    -0.54
    jść
    -0.53
     iſt
    -0.53
    POSITIVE LOGITS
    endphp
    0.51
     Transvaal
    0.48
    UnknownFields
    0.48
     errand
    0.48
     errands
    0.47
     GNP
    0.47
     snuff
    0.46
     chiefs
    0.45
     money
    0.45
     homecoming
    0.44
    Activations Density 0.025%

    No Known Activations