© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15936
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical calculations involving functions or systems

    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
     Италијани
    -1.01
     estimés
    -0.90
    ArrowToggle
    -0.88
     Italijanski
    -0.80
    Vidite
    -0.79
    はじめに
    -0.76
    ьаж
    -0.76
     disambiguazione
    -0.76
    expandindo
    -0.74
     gainera
    -0.74
    POSITIVE LOGITS
     BoxDecoration
    0.71
     AssemblyCompany
    0.71
    ReusableCell
    0.66
     BoxFit
    0.64
     cref
    0.61
     NSCoder
    0.60
    withIdentifier
    0.59
     viewType
    0.59
    nextProps
    0.59
    InputBorder
    0.58
    Activations Density 15.084%

    No Known Activations