© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72965
    Prev
    Next
    INDEX
    Explanations

    references to education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Willy
    -0.53
     Willy
    -0.46
    arlı
    -0.46
     Nacionales
    -0.44
    <bos>
    -0.44
    ------
    -0.43
    guém
    -0.43
    -----
    -0.42
    Lij
    -0.41
     Partei
    -0.41
    POSITIVE LOGITS
     Education
    1.05
     education
    1.03
    Education
    0.99
     EDUCATION
    0.94
    education
    0.93
    ducation
    0.90
     Educ
    0.88
    EDUCATION
    0.85
     EDUC
    0.83
    Educ
    0.79
    Activations Density 0.014%

    No Known Activations