© 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. 24-GEMMASCOPE-RES-16K
    11. 4183
    Prev
    Next
    INDEX
    Explanations

    references to political controversies and debates surrounding key social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following prepositions or dashes

    np_acts-logits-general · gemini-2.0-flash

    politics and policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     liné
    -0.52
    érées
    -0.51
     oamen
    -0.47
     zám
    -0.47
    ByDefault
    -0.47
     måned
    -0.46
     bedo
    -0.46
    savevideo
    -0.45
     őket
    -0.45
     înainte
    -0.44
    POSITIVE LOGITS
     Brexit
    0.96
     gun
    0.93
     climate
    0.92
     immigration
    0.91
     abortion
    0.89
     Ebola
    0.88
     opioid
    0.85
     gay
    0.85
     nuclear
    0.85
    climate
    0.82
    Activations Density 0.779%

    No Known Activations