© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4828
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "to."

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

    "to be"

    np_acts-logits-general · gemini-2.0-flash

    appears to be or seems to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.67
     ويكيميديا
    -0.67
    Kanpo
    -0.67
     une
    -0.65
    zné
    -0.65
    acterium
    -0.64
    verick
    -0.64
    ="#">
    -0.63
    antMatchers
    -0.63
    最快更新
    -0.63
    POSITIVE LOGITS
     be
    1.01
     have
    0.99
    enumi
    0.67
     been
    0.65
    have
    0.64
     defaultstate
    0.60
     явля
    0.59
     finnas
    0.58
     bý
    0.57
     belong
    0.57
    Activations Density 0.121%

    No Known Activations