© 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. 33-GEMMASCOPE-RES-16K
    11. 9027
    Prev
    Next
    INDEX
    Explanations

    references to economic needs and desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devoir
    -0.50
     gracias
    -0.45
     graças
    -0.45
    ถม
    -0.44
    おかげ
    -0.42
     remarkable
    -0.42
     zult
    -0.41
     indirectly
    -0.41
     XCTest
    -0.41
    试图
    -0.41
    POSITIVE LOGITS
     badly
    1.29
     urgently
    1.25
     desperately
    1.17
     dringend
    0.92
     ASAP
    0.89
     urgente
    0.88
     asap
    0.87
     urgent
    0.80
     desesper
    0.80
     preferably
    0.79
    Activations Density 0.418%

    No Known Activations