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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13801
    Prev
    Next
    INDEX
    Explanations

    discussions regarding political ideologies and their implications

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

    phrases describing political or ideological conflict and disagreement between groups.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vician
    -0.42
     flé
    -0.40
     Vorbild
    -0.40
     lanterna
    -0.40
     kapture
    -0.40
    눠
    -0.39
     Unterricht
    -0.39
     sắp
    -0.38
     ausz
    -0.37
     Tieren
    -0.37
    POSITIVE LOGITS
     circles
    0.90
     círculos
    0.72
     intellectuals
    0.69
     elites
    0.67
    circles
    0.67
     commentators
    0.67
     academia
    0.65
     conservatives
    0.64
     mainstream
    0.62
     critics
    0.61
    Activations Density 0.429%

    No Known Activations