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. 19-GEMMASCOPE-RES-16K
    6. 15733
    Prev
    Next
    INDEX
    Explanations

    API-related function calls and data fetching methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.96
    AccessorTable
    -0.67
     transfieras
    -0.66
     esternos
    -0.65
     оригіналу
    -0.64
     EconPapers
    -0.64
     дописавши
    -0.60
    مصادر
    -0.59
     Мексичка
    -0.58
    saraba
    -0.57
    POSITIVE LOGITS
     by
    0.71
    by
    0.63
     By
    0.54
    bys
    0.53
     berdasarkan
    0.53
    By
    0.52
     BY
    0.50
     FetchType
    0.50
    Portail
    0.49
    selectBy
    0.49
    Activations Density 0.122%

    No Known Activations