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. 11-GEMMASCOPE-RES-16K
    6. 5445
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.71
    Revenir
    -0.66
     مرئيه
    -0.61
    Catégorie
    -0.58
    OrNil
    -0.58
     protoimpl
    -0.57
    ptid
    -0.56
     disambiguazione
    -0.55
    XmlAccessorType
    -0.55
    orianCalendar
    -0.55
    POSITIVE LOGITS
    polite
    0.66
     negotiating
    0.65
     asking
    0.63
    IsMutable
    0.63
    RequestBuilder
    0.61
     Asking
    0.60
     negotiation
    0.58
    交渉
    0.57
     begging
    0.57
     requesting
    0.57
    Activations Density 0.376%

    No Known Activations