© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5424
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions related to lawsuits and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal orders or requests

    np_acts-logits-general · gemini-2.0-flash

    seeking or granting legal relief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.62
     Deliber
    -0.57
    市镇
    -0.54
     AspNetCore
    -0.53
     Autonomy
    -0.51
     autonom
    -0.51
     Acceptance
    -0.51
     privatisation
    -0.49
     GetEnumerator
    -0.47
     Autonomous
    -0.47
    POSITIVE LOGITS
     injunction
    0.93
     inj
    0.81
     order
    0.72
     contempt
    0.72
     orders
    0.71
     relief
    0.67
     restraining
    0.65
    seteq
    0.65
     ordering
    0.63
     mand
    0.63
    Activations Density 1.595%

    No Known Activations