© 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. 5-GEMMASCOPE-RES-16K
    11. 6798
    Prev
    Next
    INDEX
    Explanations

    statistical terms and measures, particularly averages and standard deviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statistical metrics related to means and standard deviations in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gonia
    -0.60
    — 
    -0.55
    icep
    -0.54
    adamia
    -0.53
     тор
    -0.53
    כשיו
    -0.52
     immunos
    -0.51
     setType
    -0.51
     exercise
    -0.50
    tikz
    -0.49
    POSITIVE LOGITS
     average
    1.60
    average
    1.55
     Average
    1.54
     averaged
    1.50
     AVERAGE
    1.49
    Average
    1.49
     averages
    1.47
    平均
    1.44
    mean
    1.41
     averaging
    1.40
    Activations Density 0.319%

    No Known Activations