© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107353
    Prev
    Next
    INDEX
    Explanations

    mentions of mayors and their offices

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

    mayor and their positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stick
    -0.49
     tratto
    -0.49
    rália
    -0.48
     Pernambuco
    -0.48
    enzial
    -0.46
    ocument
    -0.46
    Lucie
    -0.44
     числе
    -0.44
     Lucie
    -0.44
    Luca
    -0.44
    POSITIVE LOGITS
     Mayor
    1.15
    Mayor
    1.07
     mayor
    1.06
     MAYOR
    1.01
     mayors
    0.98
     sindaco
    0.90
    mayor
    0.88
     Bürgermeister
    0.73
     mayoral
    0.72
    bootstrapcdn
    0.65
    Activations Density 0.003%

    No Known Activations