© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14390
    Prev
    Next
    INDEX
    Explanations

    historical references and significant dates related to individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    eighteenth/18th century and liberty

    np_acts-logits-general · gemini-2.0-flash

    eighteenth century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.98
     propOrder
    -0.92
    SharedDtor
    -0.84
    Diwedd
    -0.82
    [@BOS@]
    -0.81
    <unused43>
    -0.80
    ðsíða
    -0.80
    <unused41>
    -0.80
    <unused8>
    -0.80
    <unused14>
    -0.80
    POSITIVE LOGITS
     […]
    0.27
     Nathan
    0.26
     James
    0.25
    branche
    0.24
    ഞ്
    0.24
     Adams
    0.24
     Adam
    0.22
     eighteenth
    0.22
     kik
    0.22
     Isaac
    0.22
    Activations Density 0.436%

    No Known Activations