© 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. 14-GEMMASCOPE-RES-16K
    6. 4916
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ago" indicating references to past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autant
    -0.77
    '.$
    -0.64
    tuta
    -0.62
    Produzione
    -0.62
     Chamb
    -0.61
    CLOS
    -0.60
     '').
    -0.59
    unus
    -0.59
     '*')
    -0.59
     Franca
    -0.59
    POSITIVE LOGITS
     ago
    1.42
     Ago
    0.92
     AGO
    0.86
    Ago
    0.83
    ago
    0.76
     atrás
    0.71
     Olms
    0.70
     sofas
    0.69
    StoryboardSegue
    0.68
     Ayer
    0.68
    Activations Density 0.074%

    No Known Activations