© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4528
    Prev
    Next
    INDEX
    Explanations

    terms related to legal obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.78
    ByExample
    -0.78
     GenerationType
    -0.77
    TypedDataSet
    -0.77
    Xna
    -0.74
    BeginContext
    -0.72
     Phari
    -0.71
    chartInstance
    -0.71
     StatefulWidget
    -0.69
     BeautifulSoup
    -0.67
    POSITIVE LOGITS
     required
    2.70
    required
    2.39
     needed
    2.32
     Required
    2.29
    Required
    2.09
     Needed
    2.02
    needed
    2.00
     REQUIRED
    1.98
     necessary
    1.91
    Needed
    1.80
    Activations Density 0.149%

    No Known Activations