© 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. 15-GEMMASCOPE-RES-16K
    6. 2760
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks and test cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreInfinity
    -0.54
    SuppressLint
    -0.51
    reuung
    -0.50
     StringTokenizer
    -0.49
    цездатний
    -0.48
     Paglinawan
    -0.47
    atschappij
    -0.47
     SqlCommand
    -0.46
     HttpNotFound
    -0.45
     Chwiliwch
    -0.45
    POSITIVE LOGITS
    UnitTesting
    1.16
     XCTest
    1.00
     Xunit
    1.00
     unittest
    0.82
    junit
    0.81
     TestCase
    0.80
     NUnit
    0.80
    scalatest
    0.79
    AndroidJUnit
    0.78
     pytest
    0.78
    Activations Density 0.222%

    No Known Activations