© 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. 10602
    Prev
    Next
    INDEX
    Explanations

    references to statistical peaks in data distributions

    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
     jo
    -0.63
    rath
    -0.63
     '
    -0.62
    ordano
    -0.60
     try
    -0.58
    .........
    -0.57
    仕
    -0.57
    Kot
    -0.56
    ...
    -0.56
     Granger
    -0.55
    POSITIVE LOGITS
     peak
    2.78
     peaks
    2.61
     Peak
    2.60
    Peak
    2.57
    peak
    2.48
     PEAK
    2.40
     Peaks
    2.28
     peaking
    2.12
    peaks
    2.11
     peaked
    1.96
    Activations Density 0.102%

    No Known Activations