© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1308
    Prev
    Next
    INDEX
    Explanations

    instances of resignation and retirement events

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

    references to personnel changes and reasons for resignation

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

    leaving roles and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Réponses
    -0.78
     betweenstory
    -0.77
      (
    -0.65
    SBATCH
    -0.65
    tilhe
    -0.64
    HtmlAttribute
    -0.64
     CURIAM
    -0.59
    writerow
    -0.59
    QMetaType
    -0.58
    PerformLayout
    -0.57
    POSITIVE LOGITS
     due
    0.96
    due
    0.80
     reasons
    0.79
     citing
    0.78
    Due
    0.75
     devido
    0.73
     amic
    0.71
     abruptly
    0.70
     Due
    0.67
     Reasons
    0.66
    Activations Density 0.109%

    No Known Activations