© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    coding terms and status messages related to file operations and server interactions

    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
    Losing
    -0.52
    ResponseWriter
    -0.50
     définiti
    -0.49
     enfans
    -0.49
    niająca
    -0.48
     bershka
    -0.48
     Rely
    -0.48
     ]
    
    -0.47
     becauſe
    -0.47
    ."),
    -0.47
    POSITIVE LOGITS
     found
    1.02
     has
    1.02
     is
    1.00
     successfully
    0.94
     was
    0.85
     available
    0.82
     taken
    0.80
     detected
    0.79
     added
    0.79
     berhasil
    0.78
    Activations Density 0.410%

    No Known Activations