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. 5763
    Prev
    Next
    INDEX
    Explanations

    Java import statements and references to servlet and Swing libraries

    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
    ren
    -0.48
     Hare
    -0.47
     referenties
    -0.47
    elizabeth
    -0.47
     alley
    -0.47
     Lizzie
    -0.47
     Macaulay
    -0.46
     متعلقه
    -0.45
     yar
    -0.45
     Flanders
    -0.45
    POSITIVE LOGITS
    swing
    1.08
     swing
    0.80
     Swing
    0.75
    Swing
    0.75
    
    0.65
    UnsafeEnabled
    0.63
     swung
    0.61
    kháu
    0.61
     swings
    0.61
    RegressionTest
    0.56
    Activations Density 0.035%

    No Known Activations