© 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. 22-GEMMASCOPE-RES-16K
    11. 9158
    Prev
    Next
    INDEX
    Explanations

    topics related to customer interactions and service quality in a retail setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding or related to dealerships/cars

    np_acts-logits-general · gemini-2.0-flash

    car dealership or sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    навли
    -0.55
    kurs
    -0.51
    '].'
    -0.51
    projeto
    -0.50
     capillary
    -0.48
    overline
    -0.48
     Jury
    -0.48
     corrector
    -0.47
     eorum
    -0.47
    costume
    -0.47
    POSITIVE LOGITS
     dealership
    1.32
     dealer
    1.27
     dealerships
    1.15
     Dealer
    1.14
     dealers
    1.07
    dealer
    1.05
    Dealer
    1.03
     Dealers
    1.02
     Deal
    1.00
    Deal
    1.00
    Activations Density 0.084%

    No Known Activations