© 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. 6408
    Prev
    Next
    INDEX
    Explanations

    elements related to environmental policy and regulations

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

    ostensibly controversial or contested

    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
     stupid
    -0.74
     correctly
    -0.71
     wisely
    -0.71
    stupid
    -0.69
     properly
    -0.66
    Proper
    -0.65
     idiot
    -0.65
     Properly
    -0.65
     idiots
    -0.65
     stupidity
    -0.64
    POSITIVE LOGITS
     controversial
    0.98
     seemingly
    0.80
     ostensibly
    0.74
     controversi
    0.73
     allegedly
    0.70
     contentious
    0.70
     polémica
    0.67
     arguably
    0.65
    contro
    0.64
     largely
    0.63
    Activations Density 0.137%

    No Known Activations