© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1418
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" and its variations

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

    forms of the verb "to be."

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

    be + adjective or state

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     itſelf
    -1.41
     alſo
    -1.32
     ſtill
    -1.28
     ftill
    -1.25
     fometimes
    -1.20
     myſelf
    -1.20
     themſelves
    -1.18
     Majefty
    -1.11
    not
    -1.11
     houſe
    -1.10
    POSITIVE LOGITS
     able
    0.93
    HAVE
    0.57
     be
    0.55
     a
    0.55
    have
    0.55
     an
    0.54
    friend
    0.53
     seen
    0.52
    get
    0.52
    atify
    0.51
    Activations Density 0.407%

    No Known Activations