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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 16187
    Prev
    Next
    INDEX
    Explanations

    concepts related to automated testing and code quality in software development

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

    Code and software testing

    np_acts-logits-general · gemini-2.0-flash

    testing and tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.73
    LEncoder
    -0.50
    PropertyGroup
    -0.49
    unmodifiable
    -0.49
    லை
    -0.47
    Bli
    -0.47
     Lew
    -0.46
     Noi
    -0.44
    cloudfront
    -0.44
     Familienname
    -0.44
    POSITIVE LOGITS
     tests
    1.69
     Tests
    1.56
     test
    1.53
     Test
    1.45
     testing
    1.41
     TESTS
    1.39
    Tests
    1.36
    Test
    1.32
     Testing
    1.31
     TEST
    1.31
    Activations Density 0.609%

    No Known Activations