© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128787
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and assumptions in the text

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

    assuming positive variable

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ſta
    -0.59
     faſt
    -0.58
     viſ
    -0.52
     ſtand
    -0.52
    المناصب
    -0.52
     ſever
    -0.50
    expandindo
    -0.49
     ſur
    -0.49
     deſt
    -0.49
     paſſ
    -0.48
    POSITIVE LOGITS
    jsxFileName
    0.46
     Plummer
    0.41
    unic
    0.40
    Gemeinden
    0.39
    biet
    0.39
    Scenario
    0.38
    setupUi
    0.37
     sei
    0.36
    Pn
    0.36
    omin
    0.36
    Activations Density 0.537%

    No Known Activations