© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    mentions of gold and related concepts

    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
     béné
    -0.53
    orteur
    -0.52
    ARIAN
    -0.50
     péné
    -0.50
     pronon
    -0.50
     abate
    -0.49
     suivante
    -0.49
    cules
    -0.48
    newArrayList
    -0.48
    woofer
    -0.48
    POSITIVE LOGITS
     plated
    0.85
     medal
    0.85
    mine
    0.75
    ilo
    0.75
     medalist
    0.75
     medals
    0.74
     Coast
    0.72
    medal
    0.71
     plating
    0.70
     coast
    0.70
    Activations Density 0.081%

    No Known Activations