© 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. 20-GEMMASCOPE-RES-16K
    11. 355
    Prev
    Next
    INDEX
    Explanations

    terms related to humanitarian aid and refugee issues

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

    Refugee assistance, aid, and international cooperation

    np_acts-logits-general · gemini-2.0-flash

    humanitarian relief for refugees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.71
     disambiguazione
    -0.65
    IndentedString
    -0.63
     consultato
    -0.55
    GEBURTSDATUM
    -0.55
    protoimpl
    -0.53
    makeConstraints
    -0.53
     Obrador
    -0.53
    addContainerGap
    -0.50
    __(/*!
    -0.48
    POSITIVE LOGITS
     humanitarian
    1.47
     relief
    1.28
     Humanitarian
    1.25
     Relief
    1.15
     aid
    1.14
     RELIEF
    1.08
    relief
    1.06
     refugee
    1.04
    Relief
    1.03
     Aid
    0.94
    Activations Density 0.128%

    No Known Activations