© 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. 5-GEMMASCOPE-RES-16K
    11. 2901
    Prev
    Next
    INDEX
    Explanations

    terms related to fat content and types of dietary fats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -1.02
    MigrationBuilder
    -0.89
    posedge
    -0.89
     EconPapers
    -0.85
    ScopeManager
    -0.83
    Personendaten
    -0.83
     AssemblyCompany
    -0.80
    RegistryLite
    -0.76
    onViewCreated
    -0.75
     '\\;'
    -0.74
    POSITIVE LOGITS
     fat
    1.84
    fat
    1.64
    Fat
    1.54
     Fat
    1.52
     fats
    1.49
     fatty
    1.49
    FAT
    1.36
     Fats
    1.33
     FAT
    1.31
     Fatty
    1.25
    Activations Density 0.384%

    No Known Activations