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. 0-GEMMASCOPE-RES-16K
    6. 7769
    Prev
    Next
    INDEX
    Explanations

    legal terminology and clauses related to liability and warranties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    screenWidth
    -0.55
     againſt
    -0.54
     screenWidth
    -0.53
     Aragon
    -0.53
     anſ
    -0.52
     uſ
    -0.52
    зопас
    -0.49
     Aton
    -0.49
    getAmount
    -0.48
     ſtill
    -0.48
    POSITIVE LOGITS
    RegressionTest
    0.80
    interpre
    0.64
    PyExc
    0.64
     interpre
    0.64
    sior
    0.63
    extAlignment
    0.63
    QMetaType
    0.62
    interpretation
    0.62
    TabStop
    0.62
     MenuView
    0.62
    Activations Density 2.922%

    No Known Activations