© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 65700
    Prev
    Next
    INDEX
    Explanations

    instances of resignations and related actions within a political context

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

    people resigning or stepping down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     integration
    -0.73
     integrate
    -0.69
     integrating
    -0.66
     integrated
    -0.66
    integrated
    -0.63
    integration
    -0.62
    Integration
    -0.62
    integrate
    -0.61
     integrations
    -0.59
    integrating
    -0.58
    POSITIVE LOGITS
     resignation
    1.73
     resign
    1.62
     resigned
    1.45
     démission
    1.40
     resigning
    1.39
    resign
    1.32
    辞职
    1.06
     renuncia
    0.99
     quit
    0.89
     इस्त
    0.87
    Activations Density 0.071%

    No Known Activations