© 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. 13209
    Prev
    Next
    INDEX
    Explanations

    instances of the act of making or creating something

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

    "making"

    np_acts-logits-general · gemini-2.0-flash

    doing and making things

    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
    GEBURTSDATUM
    -0.59
     AssemblyTitle
    -0.56
    ViewChild
    -0.53
    withIdentifier
    -0.51
    IVEREF
    -0.50
    aarrggbb
    -0.50
    évaluateur
    -0.49
    webElementXpaths
    -0.49
    MLLoader
    -0.48
    RenderAtEndOf
    -0.48
    POSITIVE LOGITS
     efectuar
    0.59
     made
    0.57
     realizó
    0.56
     effettu
    0.54
     make
    0.51
     сделан
    0.51
     efectu
    0.50
    make
    0.49
     effectuer
    0.49
     realizan
    0.49
    Activations Density 0.472%

    No Known Activations