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. 14-GEMMASCOPE-RES-16K
    6. 2904
    Prev
    Next
    INDEX
    Explanations

    references to historical disasters and significant 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
    styleType
    -0.59
     auprès
    -0.55
     الرياضيه
    -0.50
     new
    -0.50
    modelBuilder
    -0.49
    աստ
    -0.48
     variable
    -0.47
     upvote
    -0.46
     useState
    -0.46
     insuffisamment
    -0.46
    POSITIVE LOGITS
     '\\;'
    0.83
     peristiwa
    0.78
     occurred
    0.77
     événements
    0.77
     ocurrido
    0.74
     happened
    0.74
     Occur
    0.71
     fateful
    0.68
     Ereignisse
    0.68
     ocor
    0.66
    Activations Density 0.591%

    No Known Activations