© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 360
    Prev
    Next
    INDEX
    Explanations

    appearances of the letter "e" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.85
    InSection
    -0.56
    EndProject
    -0.54
    airbnb
    -0.52
    addCriterion
    -0.50
     nella
    -0.49
    ControllerTest
    -0.49
    ngdoc
    -0.48
    laravel
    -0.47
    cong
    -0.47
    POSITIVE LOGITS
     i
    0.91
     nahilalakip
    0.74
    $$
    
    0.73
    లాలు
    0.72
    Pře
    0.68
    $")
    0.66
    etheless
    0.66
     MainAxisSize
    0.63
    bibinfo
    0.63
     δη
    0.61
    Activations Density 0.315%

    No Known Activations