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. 22-GEMMASCOPE-RES-16K
    6. 14124
    Prev
    Next
    INDEX
    Explanations

    references to the Middle East

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.77
    intios
    -0.66
    Билгалдахарш
    -0.66
     ProtoMessage
    -0.65
     disambiguazione
    -0.61
    CppMethod
    -0.61
    richTextPanel
    -0.58
    gameserver
    -0.58
    Carriera
    -0.57
    invokeLater
    -0.56
    POSITIVE LOGITS
     occhiali
    0.50
    ürn
    0.47
    addPreferredGap
    0.46
    CppCodeGen
    0.45
     réguli
    0.44
     cappello
    0.44
     giapp
    0.43
     debió
    0.43
     detto
    0.43
     visibilité
    0.43
    Activations Density 0.390%

    No Known Activations