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. 16-GEMMASCOPE-RES-16K
    6. 176
    Prev
    Next
    INDEX
    Explanations

    references to traditional concepts or practices, particularly in relation to Chinese culture

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

    "traditional"

    np_acts-logits-general · gemini-2.0-flash

    traditional followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omitempty
    -0.78
     بيها
    -0.69
     newBuilder
    -0.65
     VIAF
    -0.62
    centos
    -0.58
    tauscht
    -0.57
    Espèce
    -0.54
     setShow
    -0.54
    뮬
    -0.53
     Wikidata
    -0.53
    POSITIVE LOGITS
     Traditional
    0.84
     tradi
    0.82
    Traditional
    0.79
     traditional
    0.78
    ditionally
    0.76
     traditions
    0.75
     tradition
    0.74
    thodox
    0.73
    ditional
    0.72
     glyphicon
    0.72
    Activations Density 0.105%

    No Known Activations