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. 31-GEMMASCOPE-RES-16K
    6. 15671
    Prev
    Next
    INDEX
    Explanations

    elements related to community engagement and educational programs

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

    Follows conjunctions or sentence beginnings

    np_acts-logits-general · gemini-2.0-flash

    events and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RRect
    -0.28
     (
    -0.26
    lösung
    -0.25
    fgets
    -0.25
     Füßen
    -0.25
     redenen
    -0.24
     F
    -0.24
     wensen
    -0.23
     I
    -0.23
     f
    -0.23
    POSITIVE LOGITS
     workshops
    1.30
     seminars
    1.22
     Workshops
    1.13
    Workshops
    1.12
     webinars
    1.10
     conferences
    1.06
     scholarships
    1.05
     Seminars
    1.04
     trainings
    1.02
     exhibitions
    1.00
    Activations Density 0.345%

    No Known Activations