© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6698
    Prev
    Next
    INDEX
    Explanations

    concepts related to democracy and electoral integrity

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

    references to democracy and democratic systems, institutions, or threats to them.

    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
    +#+#
    -0.55
    httphttps
    -0.52
     محفوظة
    -0.50
    adaptiveStyles
    -0.50
    WebElementEntity
    -0.50
    InitVars
    -0.49
     estratégica
    -0.44
     propOrder
    -0.44
     sibuk
    -0.44
    NameInMap
    -0.43
    POSITIVE LOGITS
     democracy
    1.77
     democratic
    1.72
     Democracy
    1.41
    democracy
    1.39
     democracies
    1.36
     democrat
    1.35
    democratic
    1.35
    Democracy
    1.31
     democracia
    1.27
    民主
    1.23
    Activations Density 0.385%

    No Known Activations