© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6564
    Prev
    Next
    INDEX
    Explanations

    references to nutritional properties and medicinal uses of plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     апель
    -0.41
    IVEREF
    -0.41
     morango
    -0.40
    りんご
    -0.38
     ябло
    -0.37
     Tomaten
    -0.37
    SharedDtor
    -0.37
    Література
    -0.37
    番茄
    -0.36
    saraba
    -0.36
    POSITIVE LOGITS
     extract
    0.75
     edible
    0.73
     extracted
    0.71
     medicinal
    0.71
     extracts
    0.70
     harvested
    0.67
     extracción
    0.65
     extraction
    0.64
     raw
    0.64
     extracting
    0.63
    Activations Density 0.466%

    No Known Activations