© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 523
    Prev
    Next
    INDEX
    Explanations

    descriptions of geographical locations and administrative divisions

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

    "Located" or place names

    np_acts-logits-general · gemini-2.0-flash

    identifying locations

    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
    MigrationBuilder
    -0.68
    LEncoder
    -0.63
    (!__
    -0.60
     ISNI
    -0.58
     ModelExpression
    -0.58
    EndInit
    -0.57
    XtraGrid
    -0.53
     mergeFrom
    -0.51
    ReusableCell
    -0.51
    uminense
    -0.50
    POSITIVE LOGITS
     located
    2.53
     Located
    2.33
     location
    2.22
     situated
    2.21
    located
    2.18
    Located
    2.18
     Location
    2.01
    location
    1.94
    Location
    1.93
     Situated
    1.89
    Activations Density 0.367%

    No Known Activations