© 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. 15-GEMMASCOPE-RES-16K
    11. 1860
    Prev
    Next
    INDEX
    Explanations

    references to respect and integrity in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.41
     manio
    -0.41
    ızı
    -0.39
    să
    -0.38
     gezin
    -0.38
     Bayou
    -0.37
     Launch
    -0.36
     launched
    -0.36
     launcher
    -0.36
    Purchases
    -0.36
    POSITIVE LOGITS
     Respect
    1.30
    Respect
    1.30
     RESPECT
    1.27
     respect
    1.25
    respect
    1.22
     respected
    1.10
     respetar
    1.07
     respectful
    1.06
     respects
    1.04
     respecting
    1.03
    Activations Density 0.198%

    No Known Activations