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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7240
    Prev
    Next
    INDEX
    Explanations

    personal pronouns describing possessions or people related to the subject plus some words that come after the pronoun and may describe them (like wife, father, powers, novel).

    oai_token-act-pair · gemini-2.0-flash

    His

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     what
    -0.73
     this
    -0.64
     the
    -0.64
    .
    -0.62
     
    -0.61
     these
    -0.58
     view
    -0.58
     like
    -0.57
     you
    -0.56
     each
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    1.26
     bezeichneter
    1.24
     disambiguazione
    1.24
    "])
    
    1.23
    :✨
    1.19
    Personensuche
    1.16
     tartalomajánló
    1.14
    ⓧ
    1.13
    parsedMessage
    1.13
    ########.
    1.13
    Activations Density 2.044%

    No Known Activations