© 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. 18-GEMMASCOPE-RES-16K
    11. 3931
    Prev
    Next
    INDEX
    Explanations

    concepts related to various communities and cultures, particularly focusing on social structures and identities

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

    Appears before location or economy-related words

    np_acts-logits-general · gemini-2.0-flash

    public, private, enterprise, geographical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.82
     resourceCulture
    -0.75
    AndEndTag
    -0.73
     reaſon
    -0.73
     pleaſure
    -0.73
     initComponents
    -0.69
     propOrder
    -0.68
     Reſ
    -0.68
     ſche
    -0.66
     ſch
    -0.65
    POSITIVE LOGITS
     economy
    0.64
     realm
    0.62
     populace
    0.62
     landscape
    0.61
     portion
    0.60
     sector
    0.58
     workforce
    0.57
     environment
    0.57
     population
    0.56
     electorate
    0.55
    Activations Density 0.847%

    No Known Activations