Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2405
    Prev
    Next
    INDEX
    Explanations

    code-related assertions and expectations in software testing

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

    "it" follows "describe" or "expect"

    np_acts-logits-general · gemini-2.0-flash

    code tests and mathematical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.72
     للمعارف
    -0.62
    WebControls
    -0.60
     محفوظة
    -0.60
    RegressionTest
    -0.56
    NewUrlParser
    -0.56
    assertEquals
    -0.55
    antMatchers
    -0.54
     proving
    -0.53
    Parcelize
    -0.51
    POSITIVE LOGITS
    expect
    0.74
    TestBed
    0.64
     TestBed
    0.61
    spyOn
    0.58
     expect
    0.52
     LoginComponent
    0.51
    osoba
    0.51
    fixture
    0.50
    shallow
    0.50
    إنه
    0.48
    Activations Density 0.083%

    No Known Activations