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. 5-GEMMASCOPE-RES-16K
    6. 13046
    Prev
    Next
    INDEX
    Explanations

    patterns of time intervals and frequencies in various contexts

    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
    '],$
    -0.57
    setopt
    -0.54
    ()]
    
    -0.52
     LXX
    -0.51
     pecados
    -0.50
     useStyles
    -0.49
    enseignements
    -0.49
     ")[
    -0.49
     CURIAM
    -0.48
     especiais
    -0.48
    POSITIVE LOGITS
     periodic
    0.97
     periodically
    0.89
     Periodic
    0.86
    Periodic
    0.83
    periodic
    0.79
     periodical
    0.77
     intervals
    0.72
     perió
    0.70
    ForValue
    0.69
     regularly
    0.68
    Activations Density 0.145%

    No Known Activations