© 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. 21-GEMMASCOPE-RES-16K
    11. 9215
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to metabolic pathways and mitochondrial function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.71
    IUrlHelper
    -0.55
     препратки
    -0.54
     transfieras
    -0.49
    FormTagHelper
    -0.48
    PhysRevD
    -0.48
    üyada
    -0.46
     caminhão
    -0.46
    angsaan
    -0.45
     Wakefield
    -0.45
    POSITIVE LOGITS
     metabolic
    0.88
     Metabolic
    0.78
     NAD
    0.75
     pyruvate
    0.73
     metabolism
    0.72
    Metabolic
    0.71
     ATP
    0.70
     carbon
    0.69
     Metabolism
    0.69
     fermentation
    0.67
    Activations Density 1.443%

    No Known Activations