© 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 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. 232
    Prev
    Next
    INDEX
    Explanations

    usage of modal verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AUTHENT
    -0.32
     middle
    -0.30
    guisement
    -0.29
     APPE
    -0.28
    GPIO
    -0.28
    uploadFile
    -0.28
     closed
    -0.28
     app
    -0.28
     sky
    -0.27
    antd
    -0.26
    POSITIVE LOGITS
     الحره
    0.68
     '\\;'
    0.68
     चीज़ों
    0.68
     otomatig
    0.67
    RenderAtEndOf
    0.65
     disambiguazione
    0.64
     Efq
    0.64
    üyada
    0.61
     للمعارف
    0.61
     Signalez
    0.61
    Activations Density 0.004%

    No Known Activations