© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 42686
    Prev
    Next
    INDEX
    Explanations

    comparative statements involving the concepts of "smaller" and "greater."

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

    comparing numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects comparative math/question prompts, especially tokens and punctuation in "Which is smaller/bigger/greater:"-style questions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.43
     @"/
    -0.35
    évaluateur
    -0.32
    IntoConstraints
    -0.31
    Viitteet
    -0.30
     linkovi
    -0.29
     /*#__
    -0.29
     hole
    -0.29
     launch
    -0.28
    ########.
    -0.28
    POSITIVE LOGITS
    enumii
    0.62
    MemoryWarning
    0.57
    RegressionTest
    0.57
    Tikang
    0.56
    owohl
    0.52
     informée
    0.52
     JpaRepository
    0.51
     either
    0.50
    DIPSETTING
    0.50
    :✨
    0.49
    Activations Density 0.190%

    No Known Activations