© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 201
    Prev
    Next
    INDEX
    Explanations

    references to specific food items and their preparation, particularly focusing on dishes like sandwiches and hamburgers

    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
    defence
    -0.82
    neighbour
    -0.82
     analysed
    -0.81
    Defence
    -0.79
     PROGRAMME
    -0.77
    ourites
    -0.77
     tyres
    -0.76
     Programmes
    -0.76
     defence
    -0.75
     нём
    -0.75
    POSITIVE LOGITS
     امريكا
    0.92
     Amish
    0.91
     Appalachian
    0.80
     HIPAA
    0.80
     Cajun
    0.77
     Haitian
    0.77
    photobucket
    0.76
     Alaskan
    0.76
     Midwest
    0.73
     Amtrak
    0.72
    Activations Density 4.342%

    No Known Activations