© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 577
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to arrest and criminal activity

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

    court and sentencing

    np_acts-logits-general · gemini-2.0-flash

    sentencing guilty conviction imprisonment

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    •Gemma-2-2B-L20-Narrative-Cluster
    Technical/Social Natural Language (criminal procedure)

    No Comments

    Negative Logits
    TestingModule
    -0.60
    ifolium
    -0.59
    AndroidJUnit
    -0.58
     وتسجيلات
    -0.56
    aarrggbb
    -0.52
    quirer
    -0.51
    PhysRevLett
    -0.49
    ofire
    -0.48
    Autoritní
    -0.48
    Collegamenti
    -0.48
    POSITIVE LOGITS
    AxisAlignment
    0.60
    QMetaType
    0.51
     magistrates
    0.50
    UrlResolution
    0.50
    MessageOf
    0.49
    pearing
    0.48
     croc
    0.48
    のこと
    0.48
     Sentence
    0.47
    SourceChecksum
    0.47
    Activations Density 0.133%

    No Known Activations