© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13151
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itaire
    -0.66
    marginHorizontal
    -0.61
    erías
    -0.59
    corazón
    -0.58
    jíma
    -0.58
     Fournier
    -0.58
     Nuevas
    -0.56
     sympa
    -0.56
    culously
    -0.56
    VIER
    -0.55
    POSITIVE LOGITS
    Be
    1.00
     Be
    0.95
    Being
    0.81
     BEING
    0.77
     Being
    0.76
    be
    0.73
     להיות
    0.71
    being
    0.71
    ToBe
    0.70
     soyez
    0.68
    Activations Density 0.152%

    No Known Activations