© 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. 16-GEMMASCOPE-RES-65K
    11. 27325
    Prev
    Next
    INDEX
    Explanations

    references to components or factors that contribute to an outcome

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

    partial causes and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.91
    Geplaatst
    -0.88
    expandindo
    -0.82
     незавершена
    -0.82
    MigrationBuilder
    -0.79
    NameInMap
    -0.75
     beginnetje
    -0.74
    最快更新
    -0.74
    AsUp
    -0.72
    OGND
    -0.71
    POSITIVE LOGITS
     also
    0.55
    iální
    0.49
    ervo
    0.48
    gründet
    0.48
    inex
    0.46
     Boe
    0.46
     Sart
    0.45
     parce
    0.45
    Also
    0.45
    hibli
    0.44
    Activations Density 0.065%

    No Known Activations