© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    key components of data processing and communication in systems, particularly focusing on the details of data packet headers and their significance for routing and interpreting data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     szól
    -0.43
    tehenden
    -0.41
    MERC
    -0.41
     készült
    -0.41
    Waga
    -0.40
     scolaires
    -0.40
     bikin
    -0.40
    母
    -0.39
     pongo
    -0.39
     domestiques
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.72
    protoimpl
    0.72
     pinulongan
    0.71
    исленность
    0.70
    :✨
    0.70
     Wiktionnaire
    0.69
     виправивши
    0.68
    ftagPool
    0.66
    yntaxException
    0.65
    曖昧さ回避
    0.65
    Activations Density 0.778%

    No Known Activations