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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3496
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction or contentment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.80
    BeginContext
    -0.77
     فريبيس
    -0.74
    InputBorder
    -0.74
    WriteAttribute
    -0.68
    AddAttribute
    -0.67
    AddTagHelper
    -0.65
    orithmic
    -0.65
     насељу
    -0.64
    сылкі
    -0.64
    POSITIVE LOGITS
     satisfied
    1.03
     satisfaction
    0.96
     contentment
    0.93
     puas
    0.88
     Satisfied
    0.87
     satisfecho
    0.85
     zufrieden
    0.85
    Satisfaction
    0.84
     contented
    0.83
     dissatisfaction
    0.83
    Activations Density 0.440%

    No Known Activations