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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9909
    Prev
    Next
    INDEX
    Explanations

    references to digital technology and online interactions

    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
     CreateTagHelper
    -0.68
     referenties
    -0.66
    }{*}{
    -0.65
     defaultstate
    -0.64
     betweenstory
    -0.58
    bootstrapcdn
    -0.58
    <?>>
    -0.58
    '>
    
    -0.58
    )}>
    -0.57
    []
    
    -0.57
    POSITIVE LOGITS
     but
    4.03
    but
    2.98
     tetapi
    2.81
     pero
    2.77
     But
    2.75
     nhưng
    2.75
    But
    2.69
     BUT
    2.54
     namun
    2.47
     tapi
    2.44
    Activations Density 3.824%

    No Known Activations