© 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. 24-GEMMASCOPE-RES-16K
    11. 3796
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to claims and petitions in the context of court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal or court documents/context

    np_acts-logits-general · gemini-2.0-flash

    legal proceedings and prior petitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.54
    $_['
    -0.51
    Personendaten
    -0.50
     seduta
    -0.50
    liothèque
    -0.49
    atmosfera
    -0.49
    htaccess
    -0.48
    Зноскі
    -0.48
    heça
    -0.48
    devamını
    -0.48
    POSITIVE LOGITS
     Learned
    0.74
    Lear
    0.72
     impug
    0.71
     learned
    0.70
    learned
    0.59
     LEARN
    0.59
     admittedly
    0.58
    tableFuture
    0.57
     petitioner
    0.57
     prays
    0.57
    Activations Density 0.260%

    No Known Activations