© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15558
    Prev
    Next
    INDEX
    Explanations

    instances of social and behavioral dynamics related to harassment and intimidation in workplace settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Etwas
    -0.94
     qualche
    -0.90
     occasionally
    -0.90
     trochu
    -0.89
     geleg
    -0.87
     lidt
    -0.86
     occasional
    -0.84
     <=",
    -0.84
     Occasionally
    -0.84
     cierta
    -0.84
    POSITIVE LOGITS
     completely
    1.60
     absolutely
    1.55
     utterly
    1.54
     incredibly
    1.50
     extremely
    1.46
     unbelievably
    1.45
     totally
    1.44
    completely
    1.34
     massively
    1.32
    extremely
    1.31
    Activations Density 1.518%

    No Known Activations