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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16343
    Prev
    Next
    INDEX
    Explanations

    pronouns or possessive pronouns followed by nouns that indicate an effect of sorts

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_token-act-pair-logits · gemini-2.0-flash

    Scientific Papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    SequentialGroup
    -0.78
    IMPORTED
    -0.56
    ConstraintMaker
    -0.54
     onBind
    -0.53
    اشی
    -0.53
    asen
    -0.49
    echt
    -0.49
    onyx
    -0.49
     distanciation
    -0.48
    Thrown
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    0.62
    toMatchSnapshot
    0.57
    };*/
    0.54
    mobileqq
    0.51
    NonQuery
    0.51
     postIndex
    0.50
     հղումներ
    0.50
     IBOutlet
    0.49
     AppColors
    0.48
    }{*}{
    0.47
    Activations Density 3.235%

    No Known Activations