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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5241
    Prev
    Next
    INDEX
    Explanations

    references to standardized testing

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

    "testing", "tests", or "benchmarks"

    np_acts-logits-general · gemini-2.0-flash

    testing and benchmarks

    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
    GraphicsUnit
    -0.70
    tvguidetime
    -0.67
    المناصب
    -0.65
    stdc
    -0.59
     rospy
    -0.57
    soever
    -0.54
    jsonwebtoken
    -0.54
    يميديا
    -0.53
    PointerException
    -0.53
     aanbod
    -0.53
    POSITIVE LOGITS
     tests
    1.81
     testing
    1.79
     test
    1.78
     Testing
    1.60
    Testing
    1.51
     Tests
    1.50
     tested
    1.48
    测试
    1.48
     Test
    1.48
    tests
    1.44
    Activations Density 0.349%

    No Known Activations