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. 21-GEMMASCOPE-RES-16K
    6. 6944
    Prev
    Next
    INDEX
    Explanations

    political opinions and discussions regarding race and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cappuccio
    -0.60
    -£
    -0.55
    Neighbour
    -0.53
     MonoBehaviour
    -0.52
     kilometre
    -0.52
    setupUi
    -0.51
     litre
    -0.49
    amssymb
    -0.49
    reda
    -0.49
     дописавши
    -0.48
    POSITIVE LOGITS
     Republicans
    1.51
     Republican
    1.45
     Obama
    1.43
     Democrats
    1.42
     presidential
    1.39
     Trump
    1.35
     President
    1.31
    Republicans
    1.29
     Democratic
    1.29
    Republican
    1.25
    Activations Density 1.237%

    No Known Activations