© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81401
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral or ethical actions and the concept of "doing the right thing."

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

    the right thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Concurrency
    -0.42
     муніципалі
    -0.41
    multer
    -0.41
    RemoveField
    -0.39
     barrister
    -0.37
    SpringBootTest
    -0.36
    Tanz
    -0.35
     ユニ
    -0.35
    Pvt
    -0.34
    rijfs
    -0.33
    POSITIVE LOGITS
     correcto
    0.71
     correcta
    0.67
    Proper
    0.64
     Proper
    0.64
    proper
    0.64
     PROPER
    0.59
     CORRECT
    0.59
     corect
    0.59
     giusta
    0.58
     richtige
    0.57
    Activations Density 0.010%

    No Known Activations