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. 6894
    Prev
    Next
    INDEX
    Explanations

    text related to the innate immune system

    oai_token-act-pair · gemini-2.0-flash

    immune

    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
     disambiguazione
    -1.05
     AspNetCore
    -0.83
    StoryboardSegue
    -0.74
     mapStateToProps
    -0.73
    ConstraintMaker
    -0.72
    XmlAccessType
    -0.68
    脚注の使い方
    -0.68
     autorytatywna
    -0.68
     <=",
    -0.67
     препратки
    -0.67
    POSITIVE LOGITS
     guardia
    0.54
     immune
    0.50
     défense
    0.49
     sanitarias
    0.49
     defenses
    0.47
     repel
    0.44
     defences
    0.44
     Immune
    0.44
     रख
    0.44
     médicas
    0.43
    Activations Density 1.326%

    No Known Activations