© 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. 36
    Prev
    Next
    INDEX
    Explanations

    legal references and terminology related to court cases and judicial proceedings

    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
     Autorisations
    -0.45
     Osiris
    -0.41
     Cupid
    -0.41
    omock
    -0.40
     paga
    -0.39
     environ
    -0.38
     blow
    -0.38
     пові
    -0.37
     Phoen
    -0.36
     defaultstate
    -0.36
    POSITIVE LOGITS
     InputDecoration
    0.71
     certiorari
    0.54
    StructEnd
    0.50
    yntaxException
    0.49
    reportWebVitals
    0.49
     suprême
    0.47
     mergeFrom
    0.47
    SharedDtor
    0.47
    minecraft
    0.46
     Justices
    0.45
    Activations Density 1.203%

    No Known Activations