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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 1281
    Prev
    Next
    INDEX
    Explanations

    terms related to political events and controversies, particularly involving elections and foreign interference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.66
    eabouts
    -0.65
    
    -0.62
    AsUp
    -0.52
     barbarians
    -0.51
    pov
    -0.51
    maco
    -0.50
    wales
    -0.49
     calendriers
    -0.49
     angekommen
    -0.49
    POSITIVE LOGITS
     BoxFit
    0.64
    SequentialGroup
    0.61
    LookAnd
    0.61
     intptr
    0.58
     Мексичка
    0.58
    GeoNames
    0.57
    sizeCache
    0.57
    futbolista
    0.57
    Gön
    0.56
    OGND
    0.55
    Activations Density 0.484%

    No Known Activations