© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 13049
    Prev
    Next
    INDEX
    Explanations

    testing-related statements and functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intima
    -0.43
    onedDateTime
    -0.37
     needle
    -0.36
    Ships
    -0.34
    JoinColumn
    -0.34
    typeorm
    -0.34
     referrerpolicy
    -0.33
    nö
    -0.32
     duran
    -0.32
    UrlResolution
    -0.32
    POSITIVE LOGITS
    describe
    1.59
    RSpec
    0.89
    beforeEach
    0.84
    UnitTesting
    0.84
     describe
    0.74
    Describe
    0.73
    scalatest
    0.69
     TestBed
    0.65
    afterEach
    0.65
     Describe
    0.64
    Activations Density 0.191%

    No Known Activations