© 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. 1916
    Prev
    Next
    INDEX
    Explanations

    words related to chocolate and its derivatives

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

    "Cho" or "Chocol" prefixes

    np_acts-logits-general · gemini-2.0-flash

    chocolate and chocolatier

    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
     stanovnika
    -0.66
     soie
    -0.63
     yyl
    -0.63
    ituary
    -0.63
     EconPapers
    -0.62
     laikā
    -0.62
     quedado
    -0.61
     benzina
    -0.60
     connexe
    -0.60
    twimg
    -0.58
    POSITIVE LOGITS
     Cho
    0.95
    Cho
    0.90
     cho
    0.78
    choc
    0.65
     choc
    0.64
     defaultstate
    0.64
    cho
    0.63
    sho
    0.62
     choco
    0.59
     Choco
    0.58
    Activations Density 0.105%

    No Known Activations