© 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. 9-GEMMASCOPE-RES-16K
    11. 15999
    Prev
    Next
    INDEX
    Explanations

    references to vehicles and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.67
     समीक्षक
    -0.57
    untura
    -0.52
    pidou
    -0.52
    пиона
    -0.51
     kasarigan
    -0.51
    SizeF
    -0.49
     Chwiliwch
    -0.48
    checkNotNull
    -0.48
     secret
    -0.47
    POSITIVE LOGITS
     vehicles
    1.00
     vehicle
    0.89
    vehicles
    0.88
     cars
    0.84
     Vehicles
    0.81
     veh
    0.79
    vehicle
    0.79
     tricycle
    0.78
     automobiles
    0.77
    Vehicles
    0.75
    Activations Density 0.252%

    No Known Activations