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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3572
    Prev
    Next
    INDEX
    Explanations

    terms related to education and its various aspects

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

    "education"

    np_acts-logits-general · gemini-2.0-flash

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.46
    guém
    -0.44
    viper
    -0.41
    toolStripButton
    -0.41
     Willoughby
    -0.41
    glyphicon
    -0.40
    nitzer
    -0.39
     Willy
    -0.39
    arlı
    -0.38
     Ghosh
    -0.38
    POSITIVE LOGITS
     education
    1.01
     Education
    1.00
    Education
    0.96
     EDUC
    0.96
     Educ
    0.95
     EDUCATION
    0.94
    Educ
    0.93
    education
    0.90
    EDUCATION
    0.88
    Edu
    0.87
    Activations Density 0.047%

    No Known Activations