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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1567
    Prev
    Next
    INDEX
    Explanations

    references to vehicle features and specifications

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

    Car models

    np_acts-logits-general · gemini-2.0-flash

    car models and series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -1.03
    setVerticalGroup
    -1.01
    ImageContext
    -0.93
    mybatisplus
    -0.92
    出版年
    -0.86
     propOrder
    -0.84
    AnimationsModule
    -0.83
    astify
    -0.79
     BoxDecoration
    -0.77
     المعيارى
    -0.76
    POSITIVE LOGITS
     Series
    0.67
     models
    0.61
     серии
    0.61
     series
    0.61
     modelu
    0.57
     моделей
    0.56
     سری
    0.56
     SERIES
    0.56
     model
    0.56
     модели
    0.55
    Activations Density 0.300%

    No Known Activations