© 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. 9-GEMMASCOPE-RES-131K
    6. 118504
    Prev
    Next
    INDEX
    Explanations

    references to the concept of guilt

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

    guilt phase

    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
     TextAppearance
    -0.57
    writerow
    -0.56
    ronique
    -0.55
     store
    -0.54
    TabLayout
    -0.54
     Mote
    -0.53
     erop
    -0.52
     Andra
    -0.51
       
    -0.51
    ❚
    -0.50
    POSITIVE LOGITS
     guilt
    1.91
     Guilt
    1.73
     guil
    0.98
     guilty
    0.93
    guilty
    0.92
    Guilty
    0.89
     Guilty
    0.88
     culpa
    0.67
     Guil
    0.63
    Guil
    0.62
    Activations Density 0.008%

    No Known Activations