© 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. 20-GEMMASCOPE-RES-16K
    6. 5436
    Prev
    Next
    INDEX
    Explanations

    phrases or constructions involving the verb "be" in various contexts

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

    "Be" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    be followed by a descriptive verb

    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
    SourceChecksum
    -0.61
    being
    -0.56
    basicConfig
    -0.55
    dafx
    -0.54
     Being
    -0.53
     bezit
    -0.53
    Being
    -0.52
    principalTable
    -0.51
     trebu
    -0.51
     auroit
    -0.51
    POSITIVE LOGITS
     easily
    1.04
     safely
    0.81
    easily
    0.80
     seen
    0.77
     chi̍t
    0.74
     Audiodateien
    0.74
     likened
    0.74
     viewed
    0.74
     facilement
    0.71
     Easily
    0.67
    Activations Density 0.148%

    No Known Activations