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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6575
    Prev
    Next
    INDEX
    Explanations

    expressions related to customer satisfaction and guarantees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    DrawerToggle
    -0.57
    rotech
    -0.56
    ريم
    -0.51
     Bial
    -0.50
    Varint
    -0.50
    onto
    -0.49
    pierw
    -0.49
     newBuilder
    -0.48
    )|^{
    -0.48
    возь
    -0.47
    POSITIVE LOGITS
     satisfied
    2.23
     satisfaction
    2.21
     happy
    2.04
     Satisfied
    1.94
     Satisfaction
    1.82
    satisfaction
    1.81
    happy
    1.80
    satisfied
    1.80
     satis
    1.75
    Satisfied
    1.75
    Activations Density 0.198%

    No Known Activations