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. 12483
    Prev
    Next
    INDEX
    Explanations

    references to the chemical "chlorophyll" or related terms

    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
    ValueStyle
    -0.63
    évaluateur
    -0.57
    hline
    -0.54
     dAtA
    -0.51
    ifer
    -0.51
    viembre
    -0.48
     PLWABN
    -0.48
     episódio
    -0.47
    DJANGO
    -0.47
    หน้านี้
    -0.47
    POSITIVE LOGITS
     Paglinawan
    0.77
     الحره
    0.66
    brainly
    0.60
    oneofs
    0.58
    rawDesc
    0.57
    **/
    
    0.56
     planètes
    0.55
     flashing
    0.53
     bpy
    0.53
     SEDS
    0.52
    Activations Density 0.090%

    No Known Activations