© 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. 340
    Prev
    Next
    INDEX
    Explanations

    annotations or metadata tags in the form of the '@' symbol

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

    references to annotations within code

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

    code documentation

    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
     hvilke
    -0.32
     además
    -0.32
    を果た
    -0.32
    IRO
    -0.32
    имость
    -0.32
    ↵
    -0.32
     esti
    -0.31
     izan
    -0.31
    ристи
    -0.31
     viso
    -0.30
    POSITIVE LOGITS
     дописавши
    1.06
     للمعارف
    1.00
     resourceCulture
    0.90
     themſelves
    0.84
    RenderAtEndOf
    0.81
    \{\\
    0.81
     Савезне
    0.80
    AndEndTag
    0.80
    ContentAsync
    0.79
     himſelf
    0.77
    Activations Density 0.017%

    No Known Activations