© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4307
    Prev
    Next
    INDEX
    Explanations

    sections marked with formatting or syntax indicators typical in structured data or code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.57
     Danza
    -0.57
    tvguidetime
    -0.55
     fubject
    -0.52
     perfons
    -0.52
     ftate
    -0.52
     mwan
    -0.51
     neceff
    -0.50
     Monfieur
    -0.50
     posterity
    -0.49
    POSITIVE LOGITS
    帖最后由
    0.75
     InputDecoration
    0.69
    waitKey
    0.66
    StoreMessageInfo
    0.63
    omiast
    0.61
    willReturn
    0.60
    зулта
    0.60
     autorytatywna
    0.59
    GetMapping
    0.57
    Erreferentziak
    0.57
    Activations Density 0.048%

    No Known Activations