© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7252
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and conversions, particularly in terms of weight and distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.88
     mile
    -0.85
    woche
    -0.76
     metre
    -0.72
     MILE
    -0.71
     byte
    -0.71
     semana
    -0.71
     Minute
    -0.70
     Woche
    -0.70
    mile
    -0.70
    POSITIVE LOGITS
     inches
    0.67
     centimeters
    0.65
     millimeters
    0.64
     pounds
    0.64
     milligrams
    0.61
     seconds
    0.61
     kilograms
    0.60
     minutes
    0.59
     hours
    0.59
     microns
    0.57
    Activations Density 0.888%

    No Known Activations