© 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. 41-GEMMASCOPE-RES-16K
    11. 9090
    Prev
    Next
    INDEX
    Explanations

    references to a specific variable or parameter labeled as "p"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Id
    -1.15
    lication
    -0.50
    Geplaatst
    -0.50
    featureID
    -0.48
    inyin
    -0.47
     незавершена
    -0.44
    ragma
    -0.43
    endence
    -0.43
     Италијани
    -0.42
    iration
    -0.40
    POSITIVE LOGITS
    MENAFN
    0.49
     CreateTagHelper
    0.43
    orced
    0.40
     médicale
    0.38
     שוליים
    0.37
     gordura
    0.35
    uck
    0.35
    ╔
    0.35
     ràng
    0.34
     acrylique
    0.34
    Activations Density 0.306%

    No Known Activations