© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7810
    Prev
    Next
    INDEX
    Explanations

    aspects related to the representation and effectiveness of legal counsel during court proceedings

    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
    ConstraintMaker
    -0.60
    TagMode
    -0.52
    Попис
    -0.44
     autorytatywna
    -0.44
    səhifə
    -0.43
     onData
    -0.43
     CreateTagHelper
    -0.42
     الرياضيه
    -0.40
    haikusbot
    -0.39
     विश्वसनीयता
    -0.39
    POSITIVE LOGITS
     lawyer
    2.61
     lawyers
    2.56
     attorneys
    2.52
     attorney
    2.50
     Lawyers
    2.16
     Lawyer
    2.16
    lawyer
    2.14
     Attorneys
    2.06
    Lawyer
    2.06
    律师
    1.97
    Activations Density 0.977%

    No Known Activations