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. 20-GEMMASCOPE-RES-16K
    6. 16058
    Prev
    Next
    INDEX
    Explanations

    references to cricket-related statistics and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selaer
    -0.61
    
    -0.60
    Voiced
    -0.56
    کنش
    -0.56
    tonsoft
    -0.55
    getColumnIndex
    -0.53
    洋
    -0.52
    gemeente
    -0.51
    MemoryWarning
    -0.49
    환
    -0.48
    POSITIVE LOGITS
     chase
    0.77
     chasing
    0.72
    CrossRef
    0.70
     chased
    0.69
     chases
    0.67
    Chasing
    0.62
    chase
    0.58
    ########.
    0.56
    chased
    0.54
     Duckworth
    0.53
    Activations Density 0.043%

    No Known Activations