© 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. 30118
    Prev
    Next
    INDEX
    Explanations

    academic qualifications and degree information

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

    previous dates and events

    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
    現在
    -0.55
     現在
    -0.55
     hoje
    -0.54
     todays
    -0.54
    الان
    -0.54
     ngayon
    -0.53
     today
    -0.52
    current
    -0.52
     idag
    -0.52
    今日
    -0.50
    POSITIVE LOGITS
     earlier
    1.22
     previous
    1.16
     Earlier
    1.15
    earlier
    1.09
     prior
    1.06
    Earlier
    1.06
     Previous
    1.02
     sebelumnya
    1.02
    previous
    0.99
     Prior
    0.98
    Activations Density 0.053%

    No Known Activations