Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2116
    Prev
    Next
    INDEX
    Explanations

    references to gold and related companies or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.62
    sproble
    -0.61
    islation
    -0.61
    ssysteme
    -0.60
     épaules
    -0.60
    ∬
    -0.59
     brancas
    -0.57
     blessés
    -0.57
     Rptr
    -0.56
     secondaires
    -0.56
    POSITIVE LOGITS
     Gold
    1.03
     GOLD
    0.98
    Gold
    0.96
     gold
    0.95
    GOLD
    0.86
    gold
    0.84
     guld
    0.72
    GOL
    0.71
     Goldie
    0.71
     Goldsmith
    0.69
    Activations Density 0.042%

    No Known Activations