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. 7657
    Prev
    Next
    INDEX
    Explanations

    emotions and states of being that express humor or intensity

    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
    rungsseite
    -1.14
    RegressionTest
    -0.95
     وتسجيلات
    -0.87
     متعلقه
    -0.85
    endregion
    -0.81
    featureID
    -0.77
    queryInterface
    -0.76
     Infórmanos
    -0.76
     distanciation
    -0.75
     BrowserModule
    -0.75
    POSITIVE LOGITS
    ness
    1.02
     enough
    0.94
    NESS
    0.90
    enough
    0.88
    neſs
    0.83
     minded
    0.81
    /-/
    0.81
     Dull
    0.79
     Curious
    0.77
     dull
    0.77
    Activations Density 0.593%

    No Known Activations