© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" and its variations

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

    "But" at the beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    introducing contrast

    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
     disambiguazione
    -0.70
     utafitiHapana
    -0.69
     leaflets
    -0.66
     balanceOf
    -0.66
     createSprite
    -0.64
    ceq
    -0.62
     Yorke
    -0.61
     ZX
    -0.61
     springfox
    -0.61
     Mero
    -0.60
    POSITIVE LOGITS
     nevertheless
    0.96
    terscotch
    0.92
    chers
    0.91
     dennoch
    0.87
     nonetheless
    0.86
     But
    0.81
    chery
    0.77
     also
    0.77
     then
    0.76
     alas
    0.76
    Activations Density 0.219%

    No Known Activations