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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 10373
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to medical experiments

    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
     thirty
    -0.72
     fifty
    -0.72
     twenty
    -0.71
     eighteen
    -0.65
     eighty
    -0.64
     sixty
    -0.63
     forty
    -0.63
     fifteen
    -0.63
     seventy
    -0.63
     ninety
    -0.62
    POSITIVE LOGITS
    
    0.65
    تقاوى
    0.63
     useHistory
    0.56
    ="">
    
    0.56
    省市镇
    0.56
     espejo
    0.52
    InstrumentedTest
    0.52
    ьаж
    0.51
    ğından
    0.50
    !("{}",
    0.50
    Activations Density 0.548%

    No Known Activations