© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 318
    Prev
    Next
    INDEX
    Explanations

    adjectives that indicate comparative or relative size, quality, or quantity

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

    relatively followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !"
    -0.39
     in
    -0.34
     pul
    -0.33
    まさに
    -0.32
    ."
    -0.32
    Attendance
    -0.32
     door
    -0.31
    AUTHOR
    -0.31
    !
    -0.31
    ゲン
    -0.30
    POSITIVE LOGITS
     relatively
    0.88
    relatively
    0.82
     Relatively
    0.80
     EconPapers
    0.77
    الدراسه
    0.75
     relativement
    0.74
     dezelve
    0.72
     comparatively
    0.71
     indisponible
    0.69
    OGND
    0.68
    Activations Density 0.019%

    No Known Activations