© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5327
    Prev
    Next
    INDEX
    Explanations

    expressions related to satisfaction and fulfillment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     O
    -0.67
     L
    -0.66
     Ne
    -0.64
     I
    -0.64
    Ne
    -0.63
     A
    -0.62
     ne
    -0.61
     
    -0.60
    ne
    -0.59
     “
    -0.58
    POSITIVE LOGITS
     Satisfaction
    1.28
     Satisfied
    1.28
    atisfaction
    1.28
     Satis
    1.27
     satisfaction
    1.27
     satisfied
    1.23
    Satisfaction
    1.22
    satisfaction
    1.21
     itſelf
    1.21
     satis
    1.20
    Activations Density 0.166%

    No Known Activations