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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6869
    Prev
    Next
    INDEX
    Explanations

    references to Marvel films and diversity

    oai_token-act-pair · gemini-2.0-flash

    MCU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -1.09
    Personensuche
    -0.71
    ględ
    -0.69
    ItemBackground
    -0.69
    DeleteBehavior
    -0.69
    OGND
    -0.68
     للمعارف
    -0.67
    ValueStyle
    -0.66
    ніципалі
    -0.66
    Aholisi
    -0.66
    POSITIVE LOGITS
    DULE
    0.44
    イビー
    0.43
    จัก
    0.42
     trilogy
    0.41
    fml
    0.40
    já
    0.40
     jasa
    0.39
    商家
    0.38
    dasarkan
    0.38
    Geme
    0.38
    Activations Density 0.469%

    No Known Activations