© 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. 3-GEMMASCOPE-RES-16K
    11. 13125
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "Swiss" or related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tableFuture
    -0.95
    parsedMessage
    -0.76
    BeginContext
    -0.68
    oredCriteria
    -0.67
     Linton
    -0.67
    saraba
    -0.66
    Mule
    -0.65
    hella
    -0.64
     ActionResult
    -0.64
     Dob
    -0.64
    POSITIVE LOGITS
     Swiss
    2.30
    Swiss
    2.06
     swiss
    1.98
     Switzerland
    1.97
    swiss
    1.74
    Switzerland
    1.70
     Suiza
    1.53
     Suisse
    1.44
     suisse
    1.44
     Schweiz
    1.35
    Activations Density 0.170%

    No Known Activations