© 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. 5-GEMMASCOPE-RES-16K
    6. 7090
    Prev
    Next
    INDEX
    Explanations

    references to eggs and related terms in the context of food production and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coroutines
    -0.71
    BDA
    -0.69
    المراجع
    -0.68
    rostis
    -0.66
    مراجع
    -0.65
     JI
    -0.64
     <.
    -0.63
     STS
    -0.62
    endphp
    -0.61
    lious
    -0.60
    POSITIVE LOGITS
     eggs
    2.79
     Eggs
    2.69
     egg
    2.63
     Egg
    2.60
    Eggs
    2.45
    Egg
    2.36
    egg
    2.32
    eggs
    2.31
     EGG
    2.15
     huevos
    1.77
    Activations Density 0.085%

    No Known Activations