© 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. 4-GEMMASCOPE-RES-16K
    6. 13008
    Prev
    Next
    INDEX
    Explanations

    phrases expressing quantity or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.63
     médicaux
    -0.62
     kropp
    -0.58
     leçons
    -0.58
     sélectionnés
    -0.57
     auroit
    -0.56
     blessures
    -0.55
     vettoriale
    -0.55
     feroit
    -0.55
     monasterio
    -0.55
    POSITIVE LOGITS
    ngdoc
    0.81
    principalTable
    0.81
     many
    0.80
     tanti
    0.78
     countless
    0.77
     виправивши
    0.77
     lot
    0.75
     nhiêu
    0.74
     CURIAM
    0.73
     myriad
    0.73
    Activations Density 0.076%

    No Known Activations