© 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. 23-GEMMASCOPE-RES-16K
    11. 5317
    Prev
    Next
    INDEX
    Explanations

    references to governmental actions and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.83
     acoper
    -0.83
     viață
    -0.81
    seamnă
    -0.80
    parsedMessage
    -0.77
     picioare
    -0.76
     noastre
    -0.76
     noastră
    -0.76
     rând
    -0.76
     entendido
    -0.72
    POSITIVE LOGITS
     con
    0.99
     pro
    0.81
     com
    0.80
     func
    0.72
     sys
    0.69
     nomi
    0.69
     elec
    0.65
     pre
    0.65
     ex
    0.65
     busi
    0.64
    Activations Density 0.224%

    No Known Activations