© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6253
    Prev
    Next
    INDEX
    Explanations

    the presence and frequency of the word "the" in the text

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

    following "the."

    np_acts-logits-general · gemini-2.0-flash

    consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totiž
    -0.86
     nemlig
    -0.81
     namelijk
    -0.74
     either
    -0.71
     firstly
    -0.70
     einerseits
    -0.69
     entweder
    -0.68
     nämlich
    -0.66
     bowiem
    -0.64
    either
    -0.64
    POSITIVE LOGITS
     consiguiente
    1.18
     consequent
    1.09
     associated
    0.99
    それに
    0.96
     accompanying
    0.95
     corresponding
    0.93
     damit
    0.92
    何より
    0.92
    corresponding
    0.92
     daarmee
    0.91
    Activations Density 0.392%

    No Known Activations