© 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. 5426
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

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

    "the" before a noun

    np_acts-logits-general · gemini-2.0-flash

    the followed by a word

    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
     Agamemnon
    -0.73
     habet
    -0.72
     myſelf
    -0.72
     Fascism
    -0.72
     Nemesis
    -0.71
     luffy
    -0.69
     Mahomet
    -0.68
     Esau
    -0.68
     raiſ
    -0.66
     pleaſure
    -0.65
    POSITIVE LOGITS
     same
    1.12
     THE
    1.05
     The
    1.03
     the
    1.01
     entire
    0.98
     latter
    0.94
    rethe
    0.94
    THE
    0.89
     whole
    0.89
    tothe
    0.87
    Activations Density 0.134%

    No Known Activations