© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8425
    Prev
    Next
    INDEX
    Explanations

    mention of quantitative analysis or specific data formats related to "qu" or "QUAD"

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

    starting with "Qu" or "QU"

    np_acts-logits-general · gemini-2.0-flash

    words starting with qu

    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
    Not in Any Lists

    No Comments

    Negative Logits
     MST
    -0.52
     isIn
    -0.47
     Internal
    -0.43
     لاس
    -0.43
    DTD
    -0.42
     Mae
    -0.42
     MDL
    -0.42
     MDS
    -0.42
     flo
    -0.42
     sf
    -0.41
    POSITIVE LOGITS
     quill
    0.93
     qu
    0.92
    Quinn
    0.92
     Quig
    0.92
    qu
    0.91
     Quij
    0.91
     quarter
    0.90
    Quin
    0.90
     Quartier
    0.89
     Qu
    0.88
    Activations Density 0.572%

    No Known Activations