© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8710
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their concentrations in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izr
    -0.56
     tyrosine
    -0.53
     grade
    -0.52
    rosine
    -0.51
     Grade
    -0.50
    grade
    -0.49
    GRADE
    -0.48
    Grade
    -0.48
     bribe
    -0.47
    nocache
    -0.46
    POSITIVE LOGITS
     gases
    1.04
     gas
    0.94
     Gases
    0.93
     balloon
    0.90
     itſelf
    0.87
     balloons
    0.82
     gaseous
    0.80
     airspace
    0.80
    ſelf
    0.80
     gás
    0.77
    Activations Density 0.526%

    No Known Activations