© 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. 10-GEMMASCOPE-RES-16K
    11. 4849
    Prev
    Next
    INDEX
    Explanations

    references to refugees and their struggles, particularly in the context of humanitarian crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discul
    -0.58
     apologize
    -0.53
    ModelSerializer
    -0.51
     bothering
    -0.51
     Ludlow
    -0.48
    plish
    -0.48
    NameInMap
    -0.48
     customization
    -0.47
    ={[
    -0.47
     honors
    -0.47
    POSITIVE LOGITS
     migrated
    0.83
    migration
    0.82
     refugees
    0.82
     migration
    0.79
     displaced
    0.79
     migrate
    0.76
    refuge
    0.75
     refugee
    0.75
     emig
    0.75
    migrations
    0.74
    Activations Density 0.240%

    No Known Activations