© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 37-GEMMASCOPE-RES-16K
    11. 7024
    Prev
    Next
    INDEX
    Explanations

    statistical methods and analyses in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seragam
    -0.37
     istrinya
    -0.36
     Beobachtung
    -0.35
     zawod
    -0.35
    deutig
    -0.34
     asiática
    -0.34
     состави
    -0.34
     respetar
    -0.34
    encodeWith
    -0.34
     osserv
    -0.34
    POSITIVE LOGITS
     regression
    0.86
     linear
    0.84
     Regression
    0.79
     Spearman
    0.77
     ANOVA
    0.77
     Linear
    0.75
     logistic
    0.69
    Linear
    0.69
     regressions
    0.69
     multivariate
    0.67
    Activations Density 1.805%

    No Known Activations