© 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. 11-GEMMASCOPE-RES-16K
    6. 4299
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "nation" and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    item
    -0.66
    tabular
    -0.65
     Gerais
    -0.65
    Gus
    -0.62
    切
    -0.58
    peutic
    -0.58
    arithmic
    -0.58
    es
    -0.58
    tral
    -0.55
    irical
    -0.55
    POSITIVE LOGITS
     nations
    1.29
     nation
    1.22
     Nation
    1.18
     NATION
    1.13
     nación
    1.08
    Nation
    1.07
     propOrder
    1.07
    Nations
    1.06
     Nations
    1.04
    NATION
    1.04
    Activations Density 0.142%

    No Known Activations