© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 16094
    Prev
    Next
    INDEX
    Explanations

    terminology related to exceptions in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    榈
    -0.36
    urlencoded
    -0.36
     ['./
    -0.35
     emplois
    -0.34
    lüğü
    -0.34
     Vermögen
    -0.33
     kobiet
    -0.32
     antiguo
    -0.32
    synthesize
    -0.32
     insgesamt
    -0.31
    POSITIVE LOGITS
     exception
    2.55
     exceptions
    2.36
    exception
    2.19
     Exceptions
    2.06
     Exception
    2.02
     excepción
    1.79
     excep
    1.78
    Exceptions
    1.74
    exceptions
    1.73
     exceptional
    1.62
    Activations Density 0.139%

    No Known Activations