© 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. 45
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to organizations and individuals

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

    references to a specific artist named Rosner

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

    names followed by 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-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
    ,
    -0.82
    からです
    -0.55
    のではなく
    -0.50
    だけでなく
    -0.50
    だけではなく
    -0.50
    <eos>
    -0.49
    themselves
    -0.49
    ?
    -0.47
     mình
    -0.47
     Bi
    -0.47
    POSITIVE LOGITS
     nevertheless
    1.25
     nonetheless
    1.25
     voici
    0.87
     חיצוניים
    0.78
     toch
    0.72
     dennoch
    0.72
    theless
    0.72
    etheless
    0.71
     ExecuteAsync
    0.71
     propOrder
    0.69
    Activations Density 0.191%

    No Known Activations