© 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. 10-GEMMASCOPE-RES-16K
    11. 16096
    Prev
    Next
    INDEX
    Explanations

    references to specific vehicles and their details in the context of criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.64
    XmlEnum
    -0.56
    LayoutStyle
    -0.55
     समीक्षक
    -0.51
    HandlerContext
    -0.49
     Paglinawan
    -0.48
    Jeografia
    -0.47
    DatabaseError
    -0.47
    béco
    -0.47
    }`).
    -0.47
    POSITIVE LOGITS
     vehicles
    1.00
     cars
    0.96
     automobiles
    0.89
    vehicles
    0.85
     vehicle
    0.84
     parked
    0.79
     Vehicles
    0.76
     automobile
    0.76
    cars
    0.73
     rented
    0.72
    Activations Density 0.342%

    No Known Activations