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. 23-GEMMASCOPE-RES-16K
    6. 11447
    Prev
    Next
    INDEX
    Explanations

    technical terms related to automotive diagnostics and the OBD-II system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.56
    ActionEvent
    -0.54
    تقاوى
    -0.52
     sanitaires
    -0.52
     שוליים
    -0.50
    webElementXpaths
    -0.50
    setDo
    -0.50
     ویکی
    -0.48
     Josephus
    -0.48
    ArrowToggle
    -0.47
    POSITIVE LOGITS
     codes
    0.89
     code
    0.81
    codes
    0.77
    Codes
    0.75
     DTC
    0.75
     OBD
    0.75
     CODES
    0.74
     Codes
    0.73
     ECU
    0.73
     programa
    0.72
    Activations Density 0.269%

    No Known Activations