© 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. 33-GEMMASCOPE-RES-16K
    6. 1134
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to defendants' rights and the judicial process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plaintiff
    -0.67
    Plaintiff
    -0.65
     plaintiffs
    -0.61
     Plaintiff
    -0.60
     PLAINTIFF
    -0.58
     lawsuit
    -0.57
     suing
    -0.57
     sued
    -0.56
     lawsuits
    -0.52
     Plaintiffs
    -0.52
    POSITIVE LOGITS
    ########.
    0.48
    Демографія
    0.47
     plea
    0.43
    IContainer
    0.42
     constitution
    0.41
     constitutional
    0.40
    cshtml
    0.40
    antMatchers
    0.39
    scriptcase
    0.39
    UnusedPrivate
    0.39
    Activations Density 3.690%

    No Known Activations