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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9162
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and testimonies in a courtroom context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.72
    resizingMask
    -0.67
    bootstrapcdn
    -0.66
    Portail
    -0.60
     <=",
    -0.59
    }\]
    -0.58
    IsContent
    -0.58
    MessageOf
    -0.58
     Laf
    -0.57
     @__
    -0.57
    POSITIVE LOGITS
    Напомним
    0.80
     שוליים
    0.67
    tahui
    0.65
    انجليز
    0.58
    قایناق‌لار
    0.54
    awaiter
    0.54
     års
    0.54
    只见
    0.53
    JvmStatic
    0.52
     sahaja
    0.51
    Activations Density 0.432%

    No Known Activations