© 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 - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9456
    Prev
    Next
    INDEX
    Explanations

    references to minor league sports teams and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geiſt
    -0.49
     فريبيس
    -0.49
    portál
    -0.47
     Waſſer
    -0.46
     queries
    -0.46
    ernoo
    -0.46
    RegistryLite
    -0.45
     dieſen
    -0.45
     ExecuteAsync
    -0.45
    ultados
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.48
    CompleteListener
    0.41
     сло
    0.38
     Superhost
    0.34
    нодоро
    0.34
    DataField
    0.33
     typelib
    0.33
    ́ng
    0.33
    lingo
    0.33
     Huck
    0.33
    Activations Density 0.386%

    No Known Activations