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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13455
    Prev
    Next
    INDEX
    Explanations

    words relating to strong emotion or depth

    oai_token-act-pair · gemini-2.0-flash

    deep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deep
    -3.00
    deep
    -2.69
    Deep
    -2.66
     Deep
    -2.64
     DEEP
    -2.45
     deeper
    -2.27
    DEEP
    -2.20
     deepest
    -2.13
     depth
    -1.94
     Deeper
    -1.88
    POSITIVE LOGITS
     bair
    0.54
    TagMode
    0.54
    SuppressMessage
    0.52
    ecap
    0.50
    CloseOperation
    0.49
     insuffisamment
    0.47
    Externí
    0.47
    liferay
    0.47
    PrototypeOf
    0.46
    matchCondition
    0.46
    Activations Density 9.986%

    No Known Activations