© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10105
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to property rights and constitutional law

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

    Legal or constitutional challenges

    np_acts-logits-general · gemini-2.0-flash

    legality and illegality claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tangentMode
    -0.41
    tagHelper
    -0.37
    oredCriteria
    -0.36
    ंदीखरीदारी
    -0.35
    APORE
    -0.34
    ResourceManager
    -0.34
    XtraReports
    -0.33
    ۪
    -0.30
     kẻ
    -0.30
     translate
    -0.30
    POSITIVE LOGITS
     unlawfully
    0.98
     illegally
    0.96
     uncons
    0.93
     illegal
    0.92
     unlawful
    0.91
     legality
    0.90
     illeg
    0.86
     lawfully
    0.84
     Illegal
    0.81
    illegal
    0.81
    Activations Density 2.218%

    No Known Activations