© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13403
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical models and regression analysis

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

    statistical methods and technical terms used in data analysis and regression modeling.

    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
    readdir
    -0.27
     jamur
    -0.26
     subordination
    -0.26
     tæn
    -0.25
     ditem
    -0.25
    inig
    -0.24
     نف
    -0.24
     ochron
    -0.23
     акку
    -0.22
     剪
    -0.22
    POSITIVE LOGITS
     fitting
    1.21
    Fitting
    1.13
     fit
    1.13
     Fitting
    1.13
    fitting
    1.08
     regression
    1.02
     Fit
    1.01
     fits
    0.98
     fitted
    0.98
     Regression
    0.96
    Activations Density 1.356%

    No Known Activations