© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4015
    Prev
    Next
    INDEX
    Explanations

    discussions about moral principles and ethics

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

    ethics and morality

    np_acts-logits-general · gemini-2.0-flash

    ethical moral standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.77
    apimachinery
    -0.69
    Története
    -0.69
     ModelExpression
    -0.66
    MLLoader
    -0.61
     configureStore
    -0.60
    */),
    -0.59
     GenerationType
    -0.57
    XmlAccessType
    -0.57
    reportWebVitals
    -0.56
    POSITIVE LOGITS
     ethics
    1.57
     morals
    1.57
     moral
    1.53
     morality
    1.51
     ethical
    1.49
     Ethics
    1.36
    moral
    1.31
    Ethics
    1.29
     Moral
    1.26
     Ethical
    1.24
    Activations Density 0.486%

    No Known Activations