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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5691
    Prev
    Next
    INDEX
    Explanations

    technical terms related to vehicle electronics and recall notifications

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

    Vehicle electronic component issues

    np_acts-logits-general · gemini-2.0-flash

    diagnostic trouble codes and vehicle modules

    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
    ContentAsync
    -0.79
    BeginInit
    -0.68
     AssemblyProduct
    -0.68
    tagHelperRunner
    -0.65
    estacks
    -0.61
    存于互联网档案馆
    -0.59
    endphp
    -0.58
     raiſ
    -0.57
    mergeFrom
    -0.57
     '\\;'
    -0.57
    POSITIVE LOGITS
     sensor
    0.71
     codes
    0.68
     solenoid
    0.61
     sensors
    0.57
     code
    0.57
     capteur
    0.56
     ECU
    0.56
     Sensor
    0.55
     wiring
    0.54
     logic
    0.54
    Activations Density 0.190%

    No Known Activations