© 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. 22-GEMMASCOPE-RES-16K
    11. 8354
    Prev
    Next
    INDEX
    Explanations

    discourse on laws and violations related to authority

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

    associated with breaking rules or laws

    np_acts-logits-general · gemini-2.0-flash

    violation of rules and laws

    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
     propOrder
    -0.77
    complexContent
    -0.77
     resourceCulture
    -0.70
    thâu
    -0.59
    Carriera
    -0.59
     Neer
    -0.56
    NewUrlParser
    -0.56
    rungsseite
    -0.56
    vlád
    -0.55
    WebElementEntity
    -0.53
    POSITIVE LOGITS
     violation
    1.94
     violate
    1.92
     violating
    1.81
     violates
    1.74
     violations
    1.71
     violated
    1.71
     breach
    1.66
    viol
    1.59
    violation
    1.53
     Violation
    1.53
    Activations Density 0.918%

    No Known Activations