© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 156
    Prev
    Next
    INDEX
    Explanations

    statistical tests and procedures used in data analysis

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

    tests or testing

    np_acts-logits-general · gemini-2.0-flash

    test and evaluation

    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
    참고
    -0.53
    ollection
    -0.51
    DockStyle
    -0.51
    abstractmethod
    -0.48
    indd
    -0.48
    idł
    -0.47
    colgroup
    -0.47
    MLLoader
    -0.45
    InstanceState
    -0.44
    Comentários
    -0.43
    POSITIVE LOGITS
     test
    2.29
     tests
    2.22
     Test
    1.94
     Tests
    1.92
    test
    1.82
    Test
    1.77
    Tests
    1.73
     TEST
    1.70
    tests
    1.66
     TESTS
    1.64
    Activations Density 0.678%

    No Known Activations