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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8374
    Prev
    Next
    INDEX
    Explanations

    cuisines and food-related terms within a dining context

    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
     Chwiliwch
    -0.48
    /*
    -0.48
    ViewImports
    -0.44
     tonight
    -0.43
     soir
    -0.42
     Lindgren
    -0.42
    évaluateur
    -0.42
    InsertCommand
    -0.42
     kveld
    -0.42
     CURIAM
    -0.42
    POSITIVE LOGITS
     breakfast
    1.41
     Breakfast
    1.20
    Breakfast
    1.18
    breakfast
    1.17
     breakfasts
    1.16
     desayuno
    1.04
     pancakes
    0.98
     desay
    0.98
     colazione
    0.95
     Frühstück
    0.94
    Activations Density 0.120%

    No Known Activations