© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1659
    Prev
    Next
    INDEX
    Explanations

    names and reference data related to Ethiopia and its context

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

    names of individuals, particularly in the context of legal discussions or significant events

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

    Ethiopian and Ethiopia

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Orrell
    -0.54
     Paco
    -0.51
    trus
    -0.50
    osgi
    -0.49
    tabria
    -0.48
    ⁢
    -0.47
     Isle
    -0.47
    DispatchToProps
    -0.46
     Westmoreland
    -0.45
    bilder
    -0.44
    POSITIVE LOGITS
     Ethiopian
    1.23
     Ethiopia
    1.18
     Ethio
    1.02
     Addis
    1.02
    Ethio
    1.02
    Ethiopia
    0.99
     Erit
    0.82
     Eritrea
    0.81
     Ababa
    0.80
    Aby
    0.77
    Activations Density 0.035%

    No Known Activations