© 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. 451
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or statistics

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

    Numbers with trailing zeros

    np_acts-logits-general · gemini-2.0-flash

    large numbers

    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
    ไตล์
    -0.42
     مشين
    -0.41
     profundos
    -0.40
     quedado
    -0.39
     aisladas
    -0.39
     confiable
    -0.39
     Мексичка
    -0.38
     seleccionado
    -0.38
     Turquía
    -0.37
     difíciles
    -0.36
    POSITIVE LOGITS
     Propag
    0.60
     the
    0.59
     Joystick
    0.58
     saniti
    0.57
     pellets
    0.57
     airpods
    0.56
     remittances
    0.56
     Peb
    0.56
     rabies
    0.56
     pulleys
    0.56
    Activations Density 0.127%

    No Known Activations