© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8894
    Prev
    Next
    INDEX
    Explanations

    recommendations and rules for table manners and dining etiquette

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

    Actions associated with eating or drinking

    np_acts-logits-general · gemini-2.0-flash

    eating and drinking

    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
     '\\;'
    -0.68
    AutoScaleMode
    -0.62
    MLLoader
    -0.62
    #
    -0.59
    kháu
    -0.58
     تضيفلها
    -0.58
    UnitTesting
    -0.55
    bewerken
    -0.53
    出版年
    -0.53
    HostException
    -0.52
    POSITIVE LOGITS
     bite
    1.17
     bites
    1.03
     mouthful
    1.02
     eating
    0.98
     Bite
    0.97
     chewing
    0.92
     chewed
    0.89
     chew
    0.89
     swallowing
    0.88
     eaten
    0.88
    Activations Density 0.156%

    No Known Activations