© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13269
    Prev
    Next
    INDEX
    Explanations

    references to diversity or variety in topics or elements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "various"

    np_acts-logits-general · gemini-2.0-flash

    various followed by diverse items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ReusableCell
    -0.65
    Mitochond
    -0.61
    PhysRevLett
    -0.59
     encre
    -0.58
    McDonald
    -0.57
    ulemon
    -0.57
    heritance
    -0.56
    iſen
    -0.56
     enfans
    -0.55
    MLLoader
    -0.54
    POSITIVE LOGITS
     various
    1.62
    various
    1.53
    Various
    1.48
     Various
    1.44
     VARIOUS
    1.24
     diverses
    1.12
     diversos
    1.02
    各种
    1.01
     berbagai
    1.00
     различные
    1.00
    Activations Density 0.186%

    No Known Activations