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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12362
    Prev
    Next
    INDEX
    Explanations

    concepts related to exploitation and fairness in relationships or interactions

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

    Exploitation or taking advantage

    np_acts-logits-general · gemini-2.0-flash

    exploitation and betrayal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    낫
    -0.50
     remit
    -0.49
     acquitted
    -0.47
    olino
    -0.47
    Palmarès
    -0.46
     abstinence
    -0.45
    >−
    -0.45
    참고
    -0.45
     enqu
    -0.44
     hal
    -0.44
    POSITIVE LOGITS
     betrayal
    1.10
     exploitation
    1.08
     betrayed
    1.08
     betray
    0.99
     Exploitation
    0.98
     exploited
    0.97
     exploiting
    0.93
     exploit
    0.92
     betraying
    0.90
     betrays
    0.86
    Activations Density 0.314%

    No Known Activations