© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 9092
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lecz
    -0.67
     său
    -0.63
     tačiau
    -0.63
     gdyż
    -0.62
     nemlig
    -0.59
     poichè
    -0.58
     např
    -0.56
     jedynie
    -0.56
     jedoch
    -0.54
     tevens
    -0.54
    POSITIVE LOGITS
     basically
    1.00
     somebody
    1.00
    basically
    0.98
     really
    0.97
    somebody
    0.94
     everybody
    0.92
    really
    0.88
    Somebody
    0.88
    Basically
    0.88
     maybe
    0.85
    Activations Density 1.642%

    No Known Activations