© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 3832
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and judicial decisions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    legal arguments and court findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.97
     tartalomajánló
    -0.91
     nahilalakip
    -0.87
    دانشنامهٔ
    -0.77
    tagHelperRunner
    -0.76
    <eos>
    -0.73
    ).}
    -0.68
    ViewFeatures
    -0.67
    </h3>
    -0.66
    ']))
    
    -0.65
    POSITIVE LOGITS
    </em>
    1.14
     ..."
    1.13
    ."
    1.07
    .”
    1.06
     …”
    1.04
    !"
    1.03
    ..."
    1.02
    !”
    1.01
    ...”
    1.00
    …"
    0.99
    Activations Density 6.019%

    No Known Activations