© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14780
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to settlement agreements and negotiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.45
    Референце
    -0.42
    addImage
    -0.40
    BagConstraints
    -0.39
     doInBackground
    -0.39
    richTextPanel
    -0.38
    Viited
    -0.38
    InvalidProtocol
    -0.37
     odm
    -0.36
     informée
    -0.36
    POSITIVE LOGITS
     settle
    3.67
     settling
    3.61
     settlement
    3.45
     settled
    3.42
     settles
    3.38
    settle
    3.33
     SETTLE
    3.20
     Settlement
    3.19
    Settle
    3.11
     Settle
    3.06
    Activations Density 0.549%

    No Known Activations