© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 12033
    Prev
    Next
    INDEX
    Explanations

    details related to experimental procedures and analyses in scientific research

    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
     faltan
    -0.51
     something
    -0.50
    +#+#
    -0.47
     longtemps
    -0.47
     what
    -0.46
     maybe
    -0.46
     even
    -0.46
     still
    -0.45
    Something
    -0.45
    是什么
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.97
     betweenstory
    0.94
     صوتيه
    0.81
     initComponents
    0.77
     Briefly
    0.75
    المناصب
    0.74
     Twelve
    0.74
    ]--;
    0.72
     hierzu
    0.71
     }}"></
    0.71
    Activations Density 1.387%

    No Known Activations