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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5348
    Prev
    Next
    INDEX
    Explanations

    expressions of hospitality and visitor engagement.

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

    technical code snippets and programming languages.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to enhancing a visitor's or customer's experience, particularly focusing on their stay, visit, or time spent at a location or with a service.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    preceding "stay" or related to hospital stays

    np_acts-logits-general · gemini-2.0-flash

    hospital stay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ldc
    -0.49
     pó
    -0.43
     Bundesrepublik
    -0.43
    indl
    -0.42
     diffusion
    -0.42
    SqlSession
    -0.40
     berge
    -0.40
     تقدم
    -0.40
     Shipping
    -0.39
    lidene
    -0.39
    POSITIVE LOGITS
     stay
    1.97
    stay
    1.74
     Stay
    1.59
     stays
    1.57
     stayed
    1.54
     visit
    1.54
     staying
    1.52
    Stay
    1.51
     STAY
    1.45
     séjour
    1.44
    Activations Density 0.117%

    No Known Activations