© 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. 24-GEMMASCOPE-RES-16K
    11. 9657
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements used in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Ingredients being mixed or added

    np_acts-logits-general · gemini-2.0-flash

    food ingredients and mixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.67
     Italijani
    -0.56
    IBOutlet
    -0.55
     uska
    -0.54
     IBOutlet
    -0.54
    новништво
    -0.54
    حياتها
    -0.54
    ίος
    -0.53
    éről
    -0.53
    miec
    -0.53
    POSITIVE LOGITS
     mixed
    0.97
    mixed
    0.80
     added
    0.75
     mélang
    0.74
     dissolved
    0.71
     gemis
    0.69
     diluted
    0.66
     mix
    0.65
     poured
    0.65
     mixture
    0.65
    Activations Density 0.240%

    No Known Activations