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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10351
    Prev
    Next
    INDEX
    Explanations

    data class definitions in Kotlin code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sap
    -0.56
    mockito
    -0.55
    ος
    -0.55
    ASX
    -0.54
    simas
    -0.51
     aleg
    -0.50
    Unfortunately
    -0.50
    ChildScrollView
    -0.50
    SYNOPSIS
    -0.48
    reactivex
    -0.48
    POSITIVE LOGITS
     Infórmanos
    0.88
    الحياه
    0.85
    Tikang
    0.72
    GEBURTSDATUM
    0.71
     FetchType
    0.68
    GenerationType
    0.68
     EconPapers
    0.67
    ParallelGroup
    0.65
    oa̍t
    0.65
    جغرافيا
    0.63
    Activations Density 0.154%

    No Known Activations