© 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. 5763
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to sending or receiving data and messages

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

    Followed by verb endings in other languages

    np_acts-logits-general · gemini-2.0-flash

    passive past/completes action

    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
     AssemblyCulture
    -0.92
    AddTagHelper
    -0.81
     المعيارى
    -0.79
    SharedCtor
    -0.73
     createSlice
    -0.72
    MLLoader
    -0.70
    UnknownFields
    -0.67
     Piston
    -0.64
     שוליים
    -0.64
    prnewswire
    -0.64
    POSITIVE LOGITS
     worden
    1.04
     wordt
    0.93
     werden
    0.87
     werd
    0.85
     wird
    0.79
     wurde
    0.78
     được
    0.78
    被
    0.72
    就被
    0.71
     wurden
    0.66
    Activations Density 0.148%

    No Known Activations