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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 930
    Prev
    Next
    INDEX
    Explanations

    educational achievements and academic qualifications

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

    Education, schooling, or courses

    np_acts-logits-general · gemini-2.0-flash

    attending educational institutions

    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
    WebElementEntity
    -0.84
    новниш
    -0.70
     ſche
    -0.61
     ſmall
    -0.60
    şört
    -0.59
    Personendaten
    -0.59
     ſen
    -0.57
    MemoryWarning
    -0.57
     leſs
    -0.57
    ſelf
    -0.57
    POSITIVE LOGITS
    ExtendWith
    0.43
     schooling
    0.39
     école
    0.36
     kurs
    0.35
     course
    0.34
    course
    0.34
     attended
    0.33
     courses
    0.32
     aprend
    0.32
     lære
    0.32
    Activations Density 0.123%

    No Known Activations