© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1653
    Prev
    Next
    INDEX
    Explanations

    guidelines related to community behavior and rules

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

    Respect, religious rules, state roads, or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    respect and religious rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     кіль
    -0.38
    NullCheck
    -0.37
     depended
    -0.36
     contado
    -0.35
    autoconfigure
    -0.35
    iastes
    -0.35
    mutlich
    -0.34
    Generic
    -0.34
    TagMode
    -0.34
     dependencia
    -0.33
    POSITIVE LOGITS
     respectful
    0.60
    Respect
    0.60
    respect
    0.60
     respect
    0.60
     Respect
    0.59
    Personendaten
    0.59
     etiquette
    0.59
     RESPECT
    0.57
     respek
    0.54
     pinulongan
    0.52
    Activations Density 0.264%

    No Known Activations