© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1769
    Prev
    Next
    INDEX
    Explanations

    terms related to Gaussian processes and statistical properties

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

    mathematical notation related to statistical distributions with zero mean.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mathematical and statistical expressions involving Gaussian distributions and their properties.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曜
    -0.38
     laude
    -0.34
    тельность
    -0.34
     IndexPath
    -0.34
     podium
    -0.34
    守
    -0.33
    nologue
    -0.33
     dring
    -0.33
     Jody
    -0.33
    PTC
    -0.32
    POSITIVE LOGITS
     variance
    0.93
     variances
    0.82
     Variance
    0.80
     mean
    0.79
    Variance
    0.77
     covariance
    0.76
    variance
    0.73
     moments
    0.71
    moments
    0.70
    covariance
    0.66
    Activations Density 1.764%

    No Known Activations