© 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. 12-GEMMASCOPE-RES-16K
    6. 6658
    Prev
    Next
    INDEX
    Explanations

    elements related to unit testing in programming, particularly in the context of test case definitions and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sumpay
    -0.49
     HttpNotFound
    -0.47
    }{*}{}
    -0.45
     unknownFields
    -0.44
    醐
    -0.43
    SuppressLint
    -0.42
     chô
    -0.42
    reuung
    -0.41
     ConstraintSet
    -0.41
    PreInfinity
    -0.40
    POSITIVE LOGITS
    UnitTesting
    1.26
     XCTest
    1.02
    MockMvc
    0.96
     Xunit
    0.93
     NUnit
    0.87
     unittest
    0.84
    ServiceTest
    0.84
     TestCase
    0.82
    RSpec
    0.82
    scalatest
    0.81
    Activations Density 0.281%

    No Known Activations