© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14718
    Prev
    Next
    INDEX
    Explanations

    mentions of political manipulation and control

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

    Infidelity, suspicion, and relationship issues

    np_acts-logits-general · gemini-2.0-flash

    infidelity and suspicious spying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QFont
    -0.52
    uldron
    -0.51
     sketch
    -0.51
     Sketch
    -0.50
    ฟ้า
    -0.50
    endphp
    -0.49
    magna
    -0.48
    StatusBadRequest
    -0.48
    теристика
    -0.46
     OnEnable
    -0.46
    POSITIVE LOGITS
     jealousy
    1.05
     jealous
    0.99
     Jealous
    0.86
    Jealous
    0.84
     spying
    0.79
     suspicions
    0.71
     celos
    0.70
     infidelity
    0.69
     accusations
    0.68
     spion
    0.66
    Activations Density 0.284%

    No Known Activations