© 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. 8087
    Prev
    Next
    INDEX
    Explanations

    locations and events related to gatherings or meetings

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

    Philippines or Philippine related topics

    np_acts-logits-general · gemini-2.0-flash

    philippines and administrative contexts

    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
    ArrowToggle
    -0.68
    __':
    -0.66
     GenerationType
    -0.62
     noires
    -0.58
    __":
    -0.57
    istoitu
    -0.56
    Sortie
    -0.55
     StatefulWidget
    -0.55
     AssemblyCulture
    -0.55
    irnov
    -0.55
    POSITIVE LOGITS
     Pili
    0.62
     philipp
    0.60
     Philippines
    0.60
    Riz
    0.56
     philippines
    0.54
     Calam
    0.54
    phils
    0.54
    DebuggerNonUser
    0.53
    PHI
    0.52
    Fil
    0.52
    Activations Density 0.072%

    No Known Activations