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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5895
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and the word "they"

    oai_token-act-pair · gemini-2.0-flash

    variations of 'thought' and 'wanted'

    np_token-act-pair-logits · gpt-4o-mini

    Thought

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     N
    -0.40
     sto
    -0.38
    ScopeManager
    -0.38
     no
    -0.37
    mingen
    -0.37
     
    -0.37
    den
    -0.36
    司
    -0.36
    matic
    -0.35
     skal
    -0.35
    POSITIVE LOGITS
     thought
    1.25
     Thought
    1.12
    Thought
    1.11
    thought
    1.09
     wanted
    1.02
    XmlAccessType
    0.98
     THOUGHT
    0.96
    wanted
    0.90
    GEBURTSDATUM
    0.89
     feared
    0.88
    Activations Density 1.663%

    No Known Activations