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. 14-GEMMASCOPE-RES-16K
    6. 3097
    Prev
    Next
    INDEX
    Explanations

    expressions related to enjoyment and pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ine
    -0.65
    netinet
    -0.64
     ggf
    -0.63
     Dalton
    -0.61
    googleapis
    -0.58
    Al
    -0.57
     Mose
    -0.57
     saith
    -0.57
    B
    -0.56
    Dalton
    -0.56
    POSITIVE LOGITS
    enjoy
    1.20
     enjoyment
    1.16
     enjoy
    1.07
     pleaſure
    1.06
     Enjoy
    1.06
    joys
    1.05
     enjoyed
    1.04
     ENJOY
    1.02
    Enjoyed
    1.01
     itſelf
    0.96
    Activations Density 0.042%

    No Known Activations