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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3386
    Prev
    Next
    INDEX
    Explanations

    phrases related to eye contact and its effects in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Catégorie
    -0.67
    <?
    -0.64
    zyka
    -0.60
     Segal
    -0.60
    CodeDom
    -0.60
    Décès
    -0.59
    swell
    -0.59
    openzeppelin
    -0.59
     Henn
    -0.59
     /\.(
    -0.58
    POSITIVE LOGITS
     gaze
    0.94
     stare
    0.92
     eyes
    0.91
     staring
    0.87
     stared
    0.85
     gazing
    0.83
     eye
    0.78
     gazed
    0.77
     Eyes
    0.76
     stares
    0.74
    Activations Density 0.098%

    No Known Activations