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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 4835
    Prev
    Next
    INDEX
    Explanations

    expressions of fatigue or weariness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.92
     ddelweddau
    -0.78
     kasarigan
    -0.74
    Personendaten
    -0.71
    Geplaatst
    -0.71
    StoryboardSegue
    -0.70
    uality
    -0.69
    RegistryLite
    -0.67
    addCriterion
    -0.65
     uuidv
    -0.62
    POSITIVE LOGITS
     fatigue
    1.09
     tired
    1.06
     boredom
    1.06
     Tired
    1.04
     boring
    1.02
     weariness
    1.00
    Boring
    0.99
    Tired
    0.99
     tiresome
    0.98
     Boring
    0.96
    Activations Density 0.159%

    No Known Activations