Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14878
    Prev
    Next
    INDEX
    Explanations

    references to traditional fermented foods and their cultural context

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

    Mentions origins or locations of something

    np_acts-logits-general · gemini-2.0-flash

    places of origin and traditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.55
     promised
    -0.47
    AnchorStyles
    -0.44
     држа
    -0.42
    喷
    -0.41
     promise
    -0.40
    פט
    -0.40
     prome
    -0.38
     droom
    -0.38
    anair
    -0.38
    POSITIVE LOGITS
     traditions
    0.93
     originated
    0.80
     originates
    0.78
     tradition
    0.77
     cultures
    0.76
     regions
    0.73
    Parcelize
    0.73
     folk
    0.72
    regions
    0.72
     Variations
    0.72
    Activations Density 0.434%

    No Known Activations