© 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. 0-GEMMASCOPE-RES-16K
    11. 3698
    Prev
    Next
    INDEX
    Explanations

    mentions of routes or paths, particularly in relation to transportation or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.66
     Irán
    -0.54
     Erwä
    -0.54
     Verhältnisse
    -0.52
     adquisición
    -0.52
     pédagogique
    -0.51
     amizade
    -0.50
     pédagog
    -0.50
     Ausführungen
    -0.49
     amistad
    -0.48
    POSITIVE LOGITS
     route
    1.37
     routes
    1.13
     ROUTE
    1.05
     Route
    1.03
    route
    0.98
     Routes
    0.96
     routing
    0.91
     rout
    0.89
     routed
    0.88
    Route
    0.87
    Activations Density 0.195%

    No Known Activations