© 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. 20-GEMMASCOPE-RES-16K
    11. 2741
    Prev
    Next
    INDEX
    Explanations

    references to devices and their usage in computing contexts

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

    computers and devices

    np_acts-logits-general · gemini-2.0-flash

    computer devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orts
    -0.40
     poch
    -0.35
     drapeau
    -0.34
     ochron
    -0.33
    ensioni
    -0.33
    insics
    -0.33
     spann
    -0.32
    aufnahme
    -0.31
     spoko
    -0.30
     ±
    -0.29
    POSITIVE LOGITS
     computers
    0.75
     computer
    0.69
    MemoryWarning
    0.66
    parsedMessage
    0.65
     hardware
    0.64
     laptop
    0.63
     AssemblyCompany
    0.62
    computers
    0.62
    HasColumnType
    0.62
     Computer
    0.60
    Activations Density 0.440%

    No Known Activations