© 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. 31-GEMMASCOPE-RES-16K
    11. 8725
    Prev
    Next
    INDEX
    Explanations

    descriptions of culinary experiences and specific food items

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

    specific food dishes and culinary descriptions in restaurant or food reviews.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poussière
    -0.49
     rente
    -0.48
     vettoriale
    -0.47
     pollici
    -0.47
     preghi
    -0.47
     virker
    -0.46
     pegat
    -0.46
    endela
    -0.46
     borse
    -0.45
     ubezpiec
    -0.44
    POSITIVE LOGITS
     delicious
    1.30
     tasty
    1.18
     culinary
    1.11
     yummy
    1.10
     tastes
    1.10
     taste
    1.10
     tasted
    1.09
     cooked
    1.06
     tasting
    1.05
     delicacies
    1.05
    Activations Density 0.583%

    No Known Activations