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. 12-GEMMASCOPE-RES-16K
    6. 5515
    Prev
    Next
    INDEX
    Explanations

    closing brackets and control flow symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.58
    ViewFeatures
    -0.54
    findpost
    -0.53
    Geplaatst
    -0.49
     intptr
    -0.49
    elemField
    -0.48
    IsMutable
    -0.48
    XmlAccessType
    -0.48
    oneofs
    -0.47
    makeConstraints
    -0.47
    POSITIVE LOGITS
     Anſ
    0.97
     myſelf
    0.86
     Monfieur
    0.80
     itſelf
    0.77
     Theſe
    0.77
     ་་
    0.75
     Reſ
    0.74
     ―――――
    0.73
     Efq
    0.71
     auffi
    0.70
    Activations Density 0.386%

    No Known Activations