© 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. 1-GEMMASCOPE-RES-16K
    6. 3991
    Prev
    Next
    INDEX
    Explanations

    terms related to tourism and hospitality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.59
    德里
    -0.57
    amente
    -0.55
    かけた
    -0.54
     avance
    -0.54
    (;;)
    -0.54
    memoized
    -0.53
    injured
    -0.52
     Scheiben
    -0.52
    nij
    -0.50
    POSITIVE LOGITS
    Guests
    0.96
     guest
    0.91
     Guests
    0.90
     tourists
    0.86
    ValueStyle
    0.85
    guest
    0.84
     Guest
    0.83
     Tourists
    0.83
     guests
    0.82
    hasMoreElements
    0.82
    Activations Density 0.073%

    No Known Activations