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. 5-GEMMASCOPE-RES-16K
    6. 8694
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aziland
    -0.98
    ysacchar
    -0.97
    AsUp
    -0.94
    BeginContext
    -0.89
     AssemblyCulture
    -0.86
     Avis
    -0.85
     CreateTagHelper
    -0.84
     jurí
    -0.83
     Gantt
    -0.83
     GeoNames
    -0.81
    POSITIVE LOGITS
     electronic
    2.13
     Electronic
    2.03
    Electronic
    1.94
    electronic
    1.92
     electronics
    1.85
     ELECTRONIC
    1.80
     elektron
    1.64
     Electronics
    1.63
    ELECTRON
    1.61
    Electronics
    1.54
    Activations Density 0.053%

    No Known Activations