© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8615
    Prev
    Next
    INDEX
    Explanations

    mentions of potato dishes and ingredients related to food

    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
    IntoConstraints
    -0.72
    AISSEE
    -0.60
    exitRule
    -0.59
     AssemblyTitle
    -0.54
     CURIAM
    -0.53
    olone
    -0.50
    IVEREF
    -0.49
    Източници
    -0.49
    Diweddarwch
    -0.48
    AddTagHelper
    -0.48
    POSITIVE LOGITS
     potatoes
    1.09
     potato
    1.07
     Potatoes
    0.96
     Potato
    0.95
     kentang
    0.91
    Potatoes
    0.88
    🥔
    0.87
     Kartoffeln
    0.84
    Potato
    0.83
    potato
    0.83
    Activations Density 0.144%

    No Known Activations