© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 202
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court rulings and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.72
    organisation
    -0.68
     organisation
    -0.67
     propOrder
    -0.66
     organisations
    -0.62
     optimised
    -0.62
     realise
    -0.62
    favourite
    -0.61
     realising
    -0.61
    behaviour
    -0.61
    POSITIVE LOGITS
     Defendants
    1.09
     Plaintiffs
    1.08
     Plaintiff
    1.05
     Defendant
    1.05
     “[
    0.95
     defendants
    0.94
     "[
    0.93
     defendant
    0.91
     plaintiffs
    0.90
     plaintiff
    0.90
    Activations Density 5.657%

    No Known Activations