© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3336
    Prev
    Next
    INDEX
    Explanations

    locations and academic institutions

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

    names of universities and institutional affiliations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     roto
    -0.34
     jet
    -0.30
    ствия
    -0.29
     effect
    -0.29
     ra
    -0.28
     Smithfield
    -0.28
     Jet
    -0.28
     Sur
    -0.28
    धन
    -0.28
    dbf
    -0.27
    POSITIVE LOGITS
    webElementXpaths
    0.71
     UO
    0.70
    الحياه
    0.65
    webElement
    0.65
     otomatig
    0.64
    lottesville
    0.61
    UGA
    0.61
     UM
    0.60
     فريبيس
    0.60
     Charlottesville
    0.59
    Activations Density 0.111%

    No Known Activations