© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7888
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to plaintiffs and defendants in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ?>/
    -0.67
     Ause
    -0.64
     كومونز
    -0.64
    ViewImports
    -0.58
    Around
    -0.58
    agle
    -0.57
    دانشنامهٔ
    -0.57
    سطس
    -0.56
     &_
    -0.56
    <?>>
    -0.56
    POSITIVE LOGITS
     plaintiff
    0.86
     defendant
    0.83
     DEFENDANT
    0.83
     Defendant
    0.77
     Plaintiff
    0.77
     plaintiffs
    0.76
    Defendant
    0.74
    Plaintiff
    0.72
     PLAINTIFF
    0.69
     Petitioner
    0.68
    Activations Density 0.589%

    No Known Activations