© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1037
    Prev
    Next
    INDEX
    Explanations

    features and characteristics related to food, specifically focusing on descriptions of dishes and their preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gouvernements
    -0.64
     enfans
    -0.63
     âmes
    -0.62
     pouvoirs
    -0.62
     χρήση
    -0.60
     cœurs
    -0.60
     prêtres
    -0.59
     dépens
    -0.59
     pères
    -0.59
     esprits
    -0.58
    POSITIVE LOGITS
     ones
    1.27
     examples
    0.96
     options
    0.90
    setVerticalGroup
    0.82
     nahilalakip
    0.82
     choices
    0.82
     للاسماء
    0.79
    Autoritní
    0.79
     varieties
    0.77
     entries
    0.77
    Activations Density 0.664%

    No Known Activations