© 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. 25-GEMMASCOPE-RES-16K
    11. 9362
    Prev
    Next
    INDEX
    Explanations

    terms related to health benefits and properties of natural compounds, particularly those with antioxidant and anti-inflammatory effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.97
    Vidite
    -0.83
    сылкі
    -0.80
    aarrggbb
    -0.71
    QMetaType
    -0.67
    KommentareTeilen
    -0.67
     CreateTagHelper
    -0.66
    حياته
    -0.61
     <=",
    -0.59
    bootstrapcdn
    -0.58
    POSITIVE LOGITS
     free
    0.67
     harmful
    0.65
     bad
    0.58
     oxidative
    0.58
    harm
    0.54
     freien
    0.53
     plaque
    0.52
     Harmful
    0.52
    free
    0.52
     pathogenic
    0.51
    Activations Density 0.613%

    No Known Activations