© 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. 22-GEMMASCOPE-RES-16K
    11. 13754
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court proceedings and actions

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

    Legal actions or proceedings

    np_acts-logits-general · gemini-2.0-flash

    filing legal actions

    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
    IsContent
    -0.82
     Audiodateien
    -0.80
     &___
    -0.70
    WebControls
    -0.65
    figuration
    -0.64
    +#+#
    -0.63
    ContentAsync
    -0.62
     Exacts
    -0.59
    ]-->
    -0.59
    JUDGE
    -0.58
    POSITIVE LOGITS
     suit
    1.21
     lawsuit
    1.06
     lawsuits
    1.01
     suits
    1.00
     litigation
    0.93
     action
    0.91
     Suit
    0.88
    suit
    0.87
     civil
    0.87
     legal
    0.81
    Activations Density 0.983%

    No Known Activations