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. 9349
    Prev
    Next
    INDEX
    Explanations

    terms related to family structures and health initiatives

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

    Precedes "should" or a variation of "should"

    np_acts-logits-general · gemini-2.0-flash

    expectation or obligation

    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
    webElementGuid
    -0.50
     OMITBAD
    -0.49
    PERATURE
    -0.48
    ‚¬
    -0.46
    [](
    -0.46
    irvana
    -0.45
    .}(
    -0.45
    álbum
    -0.44
    acer
    -0.44
    <>(
    -0.44
    POSITIVE LOGITS
     should
    3.69
    should
    3.27
     Should
    3.09
    Should
    3.05
     SHOULD
    2.68
     shouldn
    2.65
     ought
    2.62
    hould
    2.37
     Shouldn
    2.35
     shouldnt
    2.25
    Activations Density 1.747%

    No Known Activations