© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7231
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their biological properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorité
    -0.53
     NSCoder
    -0.47
     yelek
    -0.44
     enfans
    -0.42
    hæng
    -0.41
    énieur
    -0.39
     Casting
    -0.38
    Glej
    -0.38
    saraba
    -0.38
    tauan
    -0.38
    POSITIVE LOGITS
     extracts
    0.92
     phyto
    0.84
     extract
    0.83
     flavon
    0.81
     phenolic
    0.77
     Extracts
    0.74
     tannins
    0.73
     bioactive
    0.71
     sapon
    0.68
     extraction
    0.67
    Activations Density 1.223%

    No Known Activations