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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 4570
    Prev
    Next
    INDEX
    Explanations

    specific types of accommodations and amenities in vacation properties

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

    after "including"

    np_acts-logits-general · gemini-2.0-flash

    including towels

    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
     vänt
    -0.53
     commerciales
    -0.52
     CreateTagHelper
    -0.51
    Nationalité
    -0.50
     JpaRepository
    -0.48
     Accesat
    -0.47
     <>",
    -0.47
    glPushMatrix
    -0.46
     vandaag
    -0.46
     caucho
    -0.46
    POSITIVE LOGITS
     guests
    0.92
     Guests
    0.77
    Guests
    0.73
     towels
    0.71
     linens
    0.71
    guests
    0.70
     hosts
    0.69
     renter
    0.68
     host
    0.67
     Airbnb
    0.65
    Activations Density 0.031%

    No Known Activations