© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 868
    Prev
    Next
    INDEX
    Explanations

    specific food items and their descriptions

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

    Types of hot sandwiches

    np_acts-logits-general · gemini-2.0-flash

    sandwiches and burgers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.56
     addObject
    -0.54
    queurs
    -0.52
     estekak
    -0.51
    Портал
    -0.51
     rượu
    -0.50
    บาล
    -0.50
    eben
    -0.49
     समीक्षक
    -0.49
     wineries
    -0.49
    POSITIVE LOGITS
     sandwich
    1.27
     sandwiches
    1.21
     Sandwich
    1.12
    sandwich
    1.07
     Sandwiches
    1.05
    Sandwich
    1.00
     burger
    0.84
     burgers
    0.81
     hamburgers
    0.78
     hamburger
    0.76
    Activations Density 0.154%

    No Known Activations