© 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. 20-GEMMASCOPE-RES-16K
    11. 6758
    Prev
    Next
    INDEX
    Explanations

    references to food and dining experiences

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

    food descriptions, particularly focusing on ingredients, portion sizes, and culinary details.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.76
    transQ
    -0.71
    CloseOperation
    -0.61
     kasarigan
    -0.56
     pomeriggio
    -0.52
     GenerationType
    -0.51
    basicConfig
    -0.50
     kapturem
    -0.50
     wektor
    -0.48
     kapture
    -0.48
    POSITIVE LOGITS
    #
    0.35
     soggy
    0.35
     gluten
    0.34
     flattering
    0.34
     cooked
    0.33
     soft
    0.33
     chewy
    0.33
     garnish
    0.32
     gus
    0.32
     PyLong
    0.31
    Activations Density 0.068%

    No Known Activations