© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6439
    Prev
    Next
    INDEX
    Explanations

    references to political leadership and authority, particularly in relation to authoritarian behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.74
     themſelves
    -0.64
     EClass
    -0.63
     ExecuteAsync
    -0.62
     Kristus
    -0.60
     createContext
    -0.59
    migrationBuilder
    -0.58
    afficheront
    -0.56
    ();)
    -0.56
     urmă
    -0.55
    POSITIVE LOGITS
     political
    0.66
    political
    0.56
     politics
    0.56
    ContextHolder
    0.54
    politics
    0.53
     Trump
    0.53
     global
    0.52
    sonaro
    0.52
    DotNetBar
    0.52
     полити
    0.50
    Activations Density 0.420%

    No Known Activations