Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11029
    Prev
    Next
    INDEX
    Explanations

    terms related to electric vehicles and their charging systems

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

    charging or chargers

    np_acts-logits-general · gemini-2.0-flash

    charging and chargers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dued
    -0.56
    SharedCtor
    -0.54
    ffre
    -0.53
     للمعارف
    -0.52
     GeoNames
    -0.52
    reggio
    -0.52
    aksana
    -0.50
     Baillargeon
    -0.50
    PMailer
    -0.49
    exitRule
    -0.49
    POSITIVE LOGITS
     charging
    2.03
     Charging
    1.80
     charge
    1.78
    charging
    1.75
     Charge
    1.74
     charger
    1.72
    Charge
    1.68
    Charging
    1.68
    charge
    1.64
     chargers
    1.59
    Activations Density 0.108%

    No Known Activations