© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5776
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance and upkeep

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rugu
    -0.92
     déput
    -0.88
     bouteille
    -0.86
     craindre
    -0.84
     profondeur
    -0.83
    äldrar
    -0.78
     grossesse
    -0.75
     vallée
    -0.74
    thenReturn
    -0.73
     CreateTagHelper
    -0.73
    POSITIVE LOGITS
     maintenance
    2.68
     Maintenance
    2.47
    maintenance
    2.31
    Maintenance
    2.30
     MAINTENANCE
    2.12
    MAINTENANCE
    1.76
     mainten
    1.74
     mantenimiento
    1.46
     upkeep
    1.46
     maint
    1.33
    Activations Density 0.067%

    No Known Activations