Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8484
    Prev
    Next
    INDEX
    Explanations

    instances of smiling or references to smiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.69
    Trama
    -0.58
    ByPrimaryKey
    -0.57
    IsContent
    -0.57
    Tē
    -0.56
    
    -0.53
     ab
    -0.53
    principalColumn
    -0.52
    ريد
    -0.52
     near
    -0.52
    POSITIVE LOGITS
     smile
    3.68
     smiles
    3.23
     Smile
    2.95
    Smile
    2.79
    smile
    2.78
     smiling
    2.76
     smiled
    2.67
     Smiles
    2.48
     Smiling
    2.38
     sourire
    2.33
    Activations Density 0.035%

    No Known Activations