© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3485
    Prev
    Next
    INDEX
    Explanations

    themes of exploitation and self-interest, particularly in financial and power contexts

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

    Exploitation for personal gain

    np_acts-logits-general · gemini-2.0-flash

    own ambition profit greed

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    LabelTagHelper
    -0.53
     sério
    -0.47
    
    -0.45
    شهاد
    -0.42
    ModelState
    -0.41
    Innoc
    -0.41
    зион
    -0.41
     onError
    -0.41
     sentin
    -0.40
     wholes
    -0.39
    POSITIVE LOGITS
     selfish
    1.46
    selfish
    1.20
     selfishness
    1.16
     greed
    1.15
     ego
    1.08
     greedy
    1.07
     profit
    1.06
    ego
    0.97
     pecuniary
    0.95
     Ego
    0.92
    Activations Density 0.387%

    No Known Activations