© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13804
    Prev
    Next
    INDEX
    Explanations

    expressions of boredom and seeking engagement in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Boredom and amusement

    np_acts-logits-general · gemini-2.0-flash

    boredom and entertainment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protège
    -0.45
     bedrijfs
    -0.43
     vertrouwen
    -0.43
     lupo
    -0.43
    őben
    -0.42
     enkelte
    -0.42
    indépendance
    -0.41
     frequenza
    -0.40
     almak
    -0.39
     permitan
    -0.39
    POSITIVE LOGITS
     boredom
    1.98
     bored
    1.63
     entertain
    1.45
     entertainment
    1.45
     Bored
    1.30
     entertained
    1.26
     Entertainment
    1.24
    Bored
    1.23
    entertainment
    1.20
     amuse
    1.19
    Activations Density 0.217%

    No Known Activations