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. 13649
    Prev
    Next
    INDEX
    Explanations

    the phrase "back in the day" and similar phrases referencing the past

    oai_token-act-pair · gemini-2.0-flash

    day

    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
     незавершена
    -0.78
     خارجية
    -0.75
     ویکی‌پدیا
    -0.73
    RegistryLite
    -0.70
    AlterField
    -0.65
    RenderAtEndOf
    -0.61
     فريبيس
    -0.59
     Exports
    -0.56
    rungsseite
    -0.55
    >(&
    -0.54
    POSITIVE LOGITS
    <bos>
    0.83
     früher
    0.66
    時代
    0.66
     zaman
    0.65
    époque
    0.64
     heyday
    0.63
    時代の
    0.62
    فحة
    0.62
     era
    0.58
    時代に
    0.58
    Activations Density 0.782%

    No Known Activations