© 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. 40-GEMMASCOPE-RES-16K
    11. 2676
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing interpersonal dynamics or relationships, particularly those involving negative traits such as narcissism and passive-aggression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    นั้น
    -0.49
    kháu
    -0.45
     itu
    -0.39
    Халык
    -0.36
    ifrance
    -0.36
    RenderAtEndOf
    -0.35
     solches
    -0.34
    Spoljašnje
    -0.34
    onema
    -0.33
    のひとつ
    -0.33
    POSITIVE LOGITS
     who
    4.44
    who
    2.92
     whom
    2.72
     quien
    2.70
     którzy
    2.39
     whose
    2.33
     quienes
    2.28
    Who
    2.27
     quién
    2.27
     Who
    2.20
    Activations Density 2.548%

    No Known Activations