© 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. 17-GEMMASCOPE-RES-16K
    6. 13454
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparative experiences or recommendations related to food and dining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.61
    вут
    -0.50
    ﷺ
    -0.49
    tagHelperRunner
    -0.49
    netbeans
    -0.49
     ích
    -0.45
    ítő
    -0.41
     gada
    -0.41
    czegóły
    -0.41
    شهاد
    -0.41
    POSITIVE LOGITS
     Visited
    1.06
     visited
    1.06
     visiting
    1.05
    Visited
    0.98
    Visiting
    0.97
     visits
    0.96
    visited
    0.96
     Visiting
    0.90
     visit
    0.89
    visiting
    0.88
    Activations Density 0.119%

    No Known Activations