© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103840
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to intimidation or feelings of fear and pressure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.55
     BorderSide
    -0.54
     الحره
    -0.50
    rungsseite
    -0.50
     vVar
    -0.48
     Valera
    -0.48
    sidemargin
    -0.47
     '\\;'
    -0.47
    GEBURTSDATUM
    -0.46
     endregion
    -0.45
    POSITIVE LOGITS
     intimidation
    0.99
     intimidating
    0.98
     intimid
    0.94
     intimidate
    0.90
     intimidated
    0.89
     daunting
    0.56
     formidable
    0.54
     intim
    0.50
     FEAR
    0.50
     timid
    0.50
    Activations Density 0.002%

    No Known Activations