© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 345
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and formal titles and entitlements

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

    terms related to access or ownership

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

    points of entry or access

    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
    CompilerServices
    -0.76
    ItemBackground
    -0.64
    XtraBars
    -0.60
    msgTypes
    -0.59
    ^(@)
    -0.57
    SpringBootTest
    -0.56
    र्शन
    -0.54
     unknownFields
    -0.54
     AssemblyCulture
    -0.54
     InputDecoration
    -0.53
    POSITIVE LOGITS
     into
    0.72
     thereto
    0.62
     zum
    0.54
     to
    0.52
     към
    0.52
     menuju
    0.52
     hacia
    0.51
     naar
    0.49
     towards
    0.49
     toward
    0.48
    Activations Density 0.148%

    No Known Activations