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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5266
    Prev
    Next
    INDEX
    Explanations

    references to railings and their attributes in a professional context

    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
    Personendaten
    -0.77
    Приятного
    -0.71
     protoimpl
    -0.71
     '\\;'
    -0.70
     Flesh
    -0.66
    ViewImports
    -0.65
    UserScript
    -0.64
     frucht
    -0.64
    Personensuche
    -0.64
     opium
    -0.64
    POSITIVE LOGITS
     installation
    1.10
     installed
    1.02
     installers
    1.00
     install
    0.99
     installer
    0.97
     installing
    0.97
     Installation
    0.90
     design
    0.89
    Installing
    0.86
    Installation
    0.85
    Activations Density 0.190%

    No Known Activations