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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 1530
    Prev
    Next
    INDEX
    Explanations

    terms related to hotels and accommodations

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

    followed by "hotel"

    np_acts-logits-general · gemini-2.0-flash

    hotel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    provoking
    -0.69
    WebVitals
    -0.59
    Eck
    -0.58
    paksa
    -0.58
    UnsafeEnabled
    -0.57
    ❯
    -0.55
     getSize
    -0.53
    ||}
    -0.53
    giving
    -0.52
    __).
    -0.52
    POSITIVE LOGITS
     hotels
    1.40
     Hotels
    1.31
     hotel
    1.28
     HOTEL
    1.26
    Hotels
    1.24
    HOTEL
    1.18
    hotel
    1.15
    hotels
    1.14
     Hotel
    1.13
    hôtel
    1.06
    Activations Density 0.092%

    No Known Activations