© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30588
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and organizations

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

    surnames

    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
     "
    -0.65
     p
    -0.63
     
    -0.59
     (
    -0.57
     J
    -0.57
     I
    -0.56
     \
    -0.55
     ро
    -0.54
     S
    -0.54
     G
    -0.52
    POSITIVE LOGITS
     Efq
    1.34
     becauſe
    1.34
     itſelf
    1.32
     Theſe
    1.28
     ―――――
    1.27
     myſelf
    1.25
     ſeveral
    1.25
     ſy
    1.23
     himſelf
    1.22
     themſelves
    1.21
    Activations Density 1.228%

    No Known Activations