© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3976
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with legal matters or disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fil
    -0.34
     leit
    -0.32
     claws
    -0.32
     fak
    -0.31
     szak
    -0.31
     Engineers
    -0.31
    惫
    -0.31
     sink
    -0.31
    Sink
    -0.31
     engineers
    -0.31
    POSITIVE LOGITS
     mengenai
    0.94
     regarding
    0.89
     tentang
    0.88
     بشأن
    0.87
     about
    0.87
     concerning
    0.86
     Regarding
    0.84
     Concerning
    0.84
     concernant
    0.83
    Regarding
    0.83
    Activations Density 0.507%

    No Known Activations