© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12695
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation or visual assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahl
    -0.55
    casila
    -0.54
     Cider
    -0.54
     deleteById
    -0.53
     tecnológica
    -0.50
    ButtonModule
    -0.49
     eventType
    -0.48
    ymce
    -0.48
     gyhoeddwyd
    -0.47
     eventId
    -0.47
    POSITIVE LOGITS
     LOOK
    1.03
    looking
    0.98
     LOOKING
    0.98
     looking
    0.97
    Look
    0.96
     Look
    0.96
     look
    0.95
    look
    0.94
    Looking
    0.93
     Looking
    0.92
    Activations Density 0.072%

    No Known Activations