© 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 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. 5174
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables related to statistical and probabilistic concepts

    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
     
    -0.88
      
    -0.64
    <eos>
    -0.61
     /\.
    -0.51
     present
    -0.51
    <strong>
    -0.51
    <b>
    -0.50
    ↵↵
    -0.50
     er
    -0.50
     .
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.94
     Chriftian
    0.93
     jsPsych
    0.87
    SharedCtor
    0.86
     iſt
    0.85
     Majefty
    0.85
     perſon
    0.84
     Reſ
    0.84
     becauſe
    0.84
    LookAnd
    0.84
    Activations Density 3.537%

    No Known Activations