© 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. 4-GEMMASCOPE-RES-16K
    11. 1220
    Prev
    Next
    INDEX
    Explanations

    phrases referencing history or historical context

    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
     varandra
    -0.67
     дописавши
    -0.65
     RIPRODUZIONE
    -0.65
     purpoſe
    -0.64
    AddTagHelper
    -0.64
     skär
    -0.64
     Dernière
    -0.63
     démocr
    -0.63
    הערות
    -0.62
    სქოლიო
    -0.61
    POSITIVE LOGITS
     history
    1.91
     History
    1.70
    history
    1.69
    History
    1.60
     HISTORY
    1.49
     histories
    1.48
    HISTORY
    1.36
     historia
    1.24
    历史
    1.23
     historical
    1.23
    Activations Density 0.303%

    No Known Activations