© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    references to personal attributes or actions related to social status and celebrity culture

    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
    〗
    -0.42
     dévelo
    -0.42
    ollectionView
    -0.40
     ſch
    -0.39
     iload
    -0.38
     continuamente
    -0.36
     individuale
    -0.36
     eléct
    -0.36
    RectangleBorder
    -0.35
     např
    -0.35
    POSITIVE LOGITS
     courtesy
    0.88
     dammit
    0.78
     thingy
    0.77
    courtesy
    0.76
     sans
    0.72
     circa
    0.72
     goddamn
    0.72
     ala
    0.72
     lest
    0.71
     ain
    0.71
    Activations Density 1.179%

    No Known Activations