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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56614
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various forms and contexts

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

    should be + adjective/participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     parís
    -0.40
    ((
    -0.38
     noël
    -0.36
    ":"",
    -0.35
     compositeur
    -0.35
     reprend
    -0.35
     Gómez
    -0.34
    parken
    -0.34
     Nouvelles
    -0.34
    Sø
    -0.34
    POSITIVE LOGITS
     be
    1.20
     shouldBe
    0.93
     бъдат
    0.81
    ShouldBe
    0.79
     Be
    0.78
     been
    0.78
     blevet
    0.76
    writeFieldEnd
    0.76
    niſſe
    0.73
     esteja
    0.72
    Activations Density 0.030%

    No Known Activations